Daily Papers

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway (either through the adversarial attacks or via harmful assistant-prefill attacks). This raises a fundamental question: Can the innate shallow alignment in LLMs be unlocked to ensure safety at arbitrary generation depths? To achieve this goal, we propose Any-Depth Alignment (ADA), an effective inference-time defense with negligible overhead. ADA is built based on our observation that alignment is concentrated in the assistant header tokens through repeated use in shallow-refusal training, and these tokens possess the model's strong alignment priors. By reintroducing these tokens mid-stream, ADA induces the model to reassess harmfulness and recover refusals at any point in generation. Across diverse open-source model families (Llama, Gemma, Mistral, Qwen, DeepSeek, and gpt-oss), ADA achieves robust safety performance without requiring any changes to the base model's parameters. It secures a near-100% refusal rate against challenging adversarial prefill attacks ranging from dozens to thousands of tokens. Furthermore, ADA reduces the average success rate of prominent adversarial prompt attacks (such as GCG, AutoDAN, PAIR, and TAP) to below 3%. This is all accomplished while preserving utility on benign tasks with minimal over-refusal. ADA maintains this resilience even after the base model undergoes subsequent instruction tuning (benign or adversarial).

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful emergent behaviors. Through systematic analysis using the MITRE ATLAS framework, we demonstrate how 95 agents tested with access to multiple services-including browser automation, financial analysis, location tracking, and code deployment-can chain legitimate operations into sophisticated attack sequences that extend beyond the security boundaries of any individual service. These red team exercises survey whether current MCP architectures lack cross-domain security measures necessary to detect or prevent a large category of compositional attacks. We present empirical evidence of specific attack chains that achieve targeted harm through service orchestration, including data exfiltration, financial manipulation, and infrastructure compromise. These findings reveal that the fundamental security assumption of service isolation fails when agents can coordinate actions across multiple domains, creating an exponential attack surface that grows with each additional capability. This research provides a barebones experimental framework that evaluate not whether agents can complete MCP benchmark tasks, but what happens when they complete them too well and optimize across multiple services in ways that violate human expectations and safety constraints. We propose three concrete experimental directions using the existing MCP benchmark suite.

We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not reveal exactly what data agents type into which form entries during execution. To make this question measurable, we introduce MyPhoneBench, a verifiable evaluation framework for privacy behavior in mobile agents. We operationalize privacy-respecting phone use as permissioned access, minimal disclosure, and user-controlled memory through a minimal privacy contract, iMy, and pair it with instrumented mock apps plus rule-based auditing that make unnecessary permission requests, deceptive re-disclosure, and unnecessary form filling observable and reproducible. Across five frontier models on 10 mobile apps and 300 tasks, we find that task success, privacy-compliant task completion, and later-session use of saved preferences are distinct capabilities, and no single model dominates all three. Evaluating success and privacy jointly reshuffles the model ordering relative to either metric alone. The most persistent failure mode across models is simple data minimization: agents still fill optional personal entries that the task does not require. These results show that privacy failures arise from over-helpful execution of benign tasks, and that success-only evaluation overestimates the deployment readiness of current phone-use agents. All code, mock apps, and agent trajectories are publicly available at~ https://github.com/tangzhy/MyPhoneBench.

Recent advances in Audio-Language Models (ALMs) have significantly improved multimodal understanding capabilities. However, the introduction of the audio modality also brings new and unique vulnerability vectors. Previous studies have proposed jailbreak attacks that specifically target ALMs, revealing that defenses directly transferred from traditional audio adversarial attacks or text-based Large Language Model (LLM) jailbreaks are largely ineffective against these ALM-specific threats. To address this issue, we propose ALMGuard, the first defense framework tailored to ALMs. Based on the assumption that safety-aligned shortcuts naturally exist in ALMs, we design a method to identify universal Shortcut Activation Perturbations (SAPs) that serve as triggers that activate the safety shortcuts to safeguard ALMs at inference time. To better sift out effective triggers while preserving the model's utility on benign tasks, we further propose Mel-Gradient Sparse Mask (M-GSM), which restricts perturbations to Mel-frequency bins that are sensitive to jailbreaks but insensitive to speech understanding. Both theoretical analyses and empirical results demonstrate the robustness of our method against both seen and unseen attacks. Overall, \MethodName reduces the average success rate of advanced ALM-specific jailbreak attacks to 4.6% across four models, while maintaining comparable utility on benign benchmarks, establishing it as the new state of the art. Our code and data are available at https://github.com/WeifeiJin/ALMGuard.

On December 4, 2025, Anthropic released Anthropic Interviewer, an AI tool for running qualitative interviews at scale, along with a public dataset of 1,250 interviews with professionals, including 125 scientists, about their use of AI for research. Focusing on the scientist subset, I show that widely available LLMs with web search and agentic capabilities can link six out of twenty-four interviews to specific scientific works, recovering associated authors and, in some cases, uniquely identifying the interviewees. My contribution is to show that modern LLM-based agents make such re-identification attacks easy and low-effort: off-the-shelf tools can, with a few natural-language prompts, search the web, cross-reference details, and propose likely matches, effectively lowering the technical barrier. Existing safeguards can be bypassed by breaking down the re-identification into benign tasks. I outline the attack at a high level, discuss implications for releasing rich qualitative data in the age of LLM agents, and propose mitigation recommendations and open problems. I have notified Anthropic of my findings.

With the rapid evolution of foundation models, Large Language Model (LLM) agents have demonstrated increasingly powerful tool-use capabilities. However, this proficiency introduces significant security risks, as malicious actors can manipulate agents into executing tools to generate harmful content. While existing defensive mechanisms are effective, they frequently suffer from the over-refusal problem, where increased safety strictness compromises the agent's utility on benign tasks. To mitigate this trade-off, we propose SafeHarbor, a novel framework designed to establish precise decision boundaries for LLM agents. Unlike static guidelines, SafeHarbor extracts context-aware defense rules through enhanced adversarial generation. We design a local hierarchical memory system for dynamic rule injection, offering a training-free, efficient, and plug-and-play solution. Furthermore, we introduce an information entropy-based self-evolution mechanism that continuously optimizes the memory structure through dynamic node splitting and merging. Extensive experiments demonstrate that SafeHarbor achieves state-of-the-art performance on both ambiguous benign tasks and explicit malicious attacks, notably attaining a peak benign utility of 63.6\% on GPT-4o while maintaining a robust refusal rate exceeding 93\% against harmful requests. The source code is publicly available at https://github.com/ljj-cyber/SafeHarbor.

AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one trajectory, but real deployments run many agents over shared infrastructure, and the most severe risks (model-weight exfiltration, training-run poisoning) plausibly need several agents acting in concert. We initiate the empirical study of multi-agent AI control, formalising distributed attacks in which several agents jointly aim for a malicious goal. We develop FakeLab: a synthetic AI-lab codebase (9 services, 86 benign tasks, 4 attack objectives). We evaluate single agent monitoring against distributed attacks, varying the number of agents, their coordination, model capabilities and precise monitoring configuration. Our central finding is the fragmentation effect: as more agents coordinate to attack, per-agent monitoring becomes less likely to catch any of the attackers. Secondly, this is not driven by the ratio of benign to malicious code -- we argue this is likely dependent on model capability. Third, an explicit planner amplifies the fragmentation effect, raises the rate of completing the attack up to sevenfold, and mildly sharpens executors' poor monitor-theory-of-mind. Finally: a weak "trusted" monitor misses most attacks, while a stronger one cuts undetected success by more than an order of magnitude but remains imperfect. We are happy to share FakeLab, our control setting, with safety researchers on request.

Large Language Models (LLMs), despite advances in safety alignment, remain vulnerable to jailbreak attacks designed to circumvent protective mechanisms. Prevailing defense strategies rely on external interventions, such as input filtering or output modification, which often lack generalizability and compromise model utility while incurring significant computational overhead. In this work, we introduce a new, training-free defense paradigm, Self-Activating Internal Defense (SAID), which reframes the defense task from external correction to internal capability activation. SAID uniquely leverages the LLM's own reasoning abilities to proactively identify and neutralize malicious intent through a three-stage pipeline: model-native intent distillation to extract core semantics, optimal safety prefix probing to activate latent safety awareness, and a conservative aggregation strategy to ensure robust decision-making. Extensive experiments on five open-source LLMs against six advanced jailbreak attacks demonstrate that SAID substantially outperforms state-of-the-art defenses in reducing harmful outputs. Crucially, it achieves this while preserving model performance on benign tasks and incurring minimal computational overhead. Our work establishes that activating the intrinsic safety mechanisms of LLMs is a more robust and scalable path toward building safer and more reliable aligned AI systems.

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent backdoor attacks, overlooking the novel attack surfaces introduced by agent collaboration in MAS. To bridge this gap, we present the first Distributed Backdoor Attack tailored to MAS. We decompose the backdoor into multiple distributed attack primitives that are embedded within MAS tools. These primitives remain dormant individually but collectively activate only when agents collaborate in a specific sequence, thereby assembling the full backdoor to execute targeted attacks such as data exfiltration. To fully assess this threat, we introduce a benchmark for multi-role collaborative tasks and a sandboxed framework to evaluate. Extensive experiments demonstrate that our attack achieves an attack success rate exceeding 95% without degrading performance on benign tasks. This work exposes novel backdoor attack surfaces that exploit agent collaboration, underscoring the need to move beyond single-agent protection. Code and benchmark are available at https://github.com/whfeLingYu/Distributed-Backdoor-Attacks-in-MAS.

Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly safe answer. Existing safety-alignment signals are largely response-level or off-policy, and often incur a safety-utility trade-off: improving agent safety comes at the cost of degraded task performance. Such sparse and single-objective rewards severely limit real-world usability. To bridge this gap, we propose FATE, an on-policy self-evolving framework that transforms verifier-scored failures into repair supervision without expert demonstrations. For each failure, the same policy proposes repair candidates, which are then re-scored by verifiers and filtered across security, utility, over-refusal control, and trajectory validity. This dense trajectory-level information is then used as a supervision signal for agent self-evolution. During this process, we further introduce Pareto-Front Policy Optimization (PFPO), combining supervised warmup with Pareto-aware policy optimization to preserve safety-utility trade-offs. Experiments on AgentDojo, AgentHarm, and ATBench show that FATE improves safety across different models and scales while preserving useful behavior. Compared with strong baselines, FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%. These results suggest that failed trajectories can provide structured repair supervision for safer self-evolving agents.

Recently, language models like Llama 3.1 Instruct have become increasingly capable of agentic behavior, enabling them to perform tasks requiring short-term planning and tool use. In this study, we apply refusal-vector ablation to Llama 3.1 70B and implement a simple agent scaffolding to create an unrestricted agent. Our findings imply that these refusal-vector ablated models can successfully complete harmful tasks, such as bribing officials or crafting phishing attacks, revealing significant vulnerabilities in current safety mechanisms. To further explore this, we introduce a small Safe Agent Benchmark, designed to test both harmful and benign tasks in agentic scenarios. Our results imply that safety fine-tuning in chat models does not generalize well to agentic behavior, as we find that Llama 3.1 Instruct models are willing to perform most harmful tasks without modifications. At the same time, these models will refuse to give advice on how to perform the same tasks when asked for a chat completion. This highlights the growing risk of misuse as models become more capable, underscoring the need for improved safety frameworks for language model agents.

This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a state in which they continuously generate harmful content while executing otherwise benign tasks. We introduce TVD (Task, Validator, Data), a framework that triggers ISC through domain tasks where generating harmful content is the only valid completion, and construct ISC-Bench containing 53 scenarios across 8 professional disciplines. Evaluated on JailbreakBench, three representative scenarios yield worst-case safety failure rates averaging 95.3% across four frontier LLMs (including GPT-5.2 and Claude Sonnet 4.5), substantially exceeding standard jailbreak attacks. Frontier models are more vulnerable than earlier LLMs: the very capabilities that enable complex task execution become liabilities when tasks intrinsically involve harmful content. This reveals a growing attack surface: almost every professional domain uses tools that process sensitive data, and each new dual-use tool automatically expands this vulnerability--even without any deliberate attack. Despite substantial alignment efforts, frontier LLMs retain inherently unsafe internal capabilities: alignment reshapes observable outputs but does not eliminate the underlying risk profile. These findings underscore the need for caution when deploying LLMs in high-stakes settings. Source code: https://github.com/wuyoscar/ISC-Bench

Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required specialized expertise, tailored algorithms, and manual corroboration. We show that LLM-based agents weaken this barrier: by combining scattered, individually non-identifying cues with public evidence, they reconstruct real-world identities, sometimes even during benign tasks. We evaluate this risk across three settings -- classical linkage incidents, a controlled benchmark (InferLink) that varies fingerprint type, task framing, and attacker knowledge, and open-ended human--AI interaction traces. In the sparsest regime of the Netflix Prize deanonymization setting, agents reconstruct 79.2\% of identities, against 56.0\% for a classical matching baseline; on InferLink, they link individuals even without an explicit re-identification request, and more often once one is given. In redacted human--AI interaction traces, agents further resolve anonymized profiles to specific individuals by corroborating contextual cues with public evidence. These findings suggest that privacy evaluations for agentic systems should measure not only what information is accessed or disclosed, but also what identities can be inferred.

Prompt injection is one of the most critical vulnerabilities in LLM agents; yet, effective automated attacks remain largely unexplored from an optimization perspective. Existing methods heavily depend on human red-teamers and hand-crafted prompts, limiting their scalability and adaptability. We propose AutoInject, a reinforcement learning framework that generates universal, transferable adversarial suffixes while jointly optimizing for attack success and utility preservation on benign tasks. Our black-box method supports both query-based optimization and transfer attacks to unseen models and tasks. Using only a 1.5B parameter adversarial suffix generator, we successfully compromise frontier systems including GPT 5 Nano, Claude Sonnet 3.5, and Gemini 2.5 Flash on the AgentDojo benchmark, establishing a stronger baseline for automated prompt injection research.

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks to enhance their proficiency. However, safety concerns are frequently overlooked during this fine-tuning process. In this work, we show that aligned LLMs can become unintentionally misaligned, leading to a higher likelihood of executing harmful tasks and a reduced tendency to refuse them when fine-tuned to execute agentic tasks. To address these safety challenges, we propose Prefix INjection Guard (PING), a simple yet effective method that prepends automatically generated natural language prefixes to agent responses, guiding them to refuse harmful requests while preserving performance on benign tasks. Specifically, we introduce an iterative approach that alternates between (1) generating candidate prefixes and (2) selecting those that optimize both task performance and refusal behavior. Experimental results demonstrate that PING significantly enhances the safety of fine-tuned LLM agents without sacrificing their effectiveness. PING consistently outperforms existing prompting approaches across diverse benchmarks in both web navigation and code generation tasks. Our analysis of internal hidden states via linear probes reveals that prefix tokens are crucial for behavior modification, explaining the performance gains. WARNING: This paper contains contents that are unethical or offensive in nature.

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that superficially resemble harmful content. This phenomena diminishes utility in production applications that repeatedly rely on common prompt templates or applications that frequently rely on LLMs for specific tasks (e.g. sentiment analysis, language translation). Through comprehensive evaluation, we demonstrate that LLMs still tend to refuse responses to harmful instructions when those instructions are reframed to appear as benign tasks. Our mechanistic analysis reveal that LLMs follow distinct "constellation" patterns in embedding space as representations traverse layers, with each task maintaining consistent trajectories that shift predictably between refusal and non-refusal cases. We introduce SafeConstellations, an inference-time trajectory-shifting approach that tracks task-specific trajectory patterns and guides representations toward non-refusal pathways. By selectively guiding model behavior only on tasks prone to over-refusal, and by preserving general model behavior, our method reduces over-refusal rates by up to 73% with minimal impact on utility-offering a principled approach to mitigating over-refusals.

Large language models (LLMs) have revolutionized natural language processing with their ability to generate coherent and contextually relevant text. However, their deployment raises significant concerns about the potential for generating harmful or inappropriate content. In this paper, we introduce Progressive Self-Reflection (PSR), a novel inference-time technique that empowers LLMs to self-monitor and correct their outputs dynamically. Experimental results demonstrate that applying our proposed method to Llama-3.1-8B-Instruct reduces the attack success rate from 77.5\% to 5.9\%, to Llama-3.1-8B base from 89.7\% to 5.6\%, and to Qwen2.5-7B-Instruct from 44.4\% to 3.8\%, without additional training, while maintaining their original performance on benign tasks. Our approach acts as a test-time scaling method, where additional self-reflection rounds enhance safety at the cost of inference overhead. To balance safety with computational efficiency, we introduce a lightweight self-reflection predictor that estimates the optimal number of reflection rounds based on input complexity. This adaptive mechanism prevents unnecessary self-assessment on benign inputs while ensuring thorough evaluation when encountering potentially harmful content. Our findings suggest that Progressive Self-Reflection serves as a scalable test-time approach, enhancing LLM safety by dynamically allocating computational resources in proportion to the input's risk profile.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduces a new attack surface: the routing mechanism that determines which experts process each input. Prior work shows that manipulating routing can bypass safety alignment, but existing attacks require model modification and thus apply only to locally deployed models. By contrast, real-world LLM services are remotely hosted and accessible only through input queries. This raises a fundamental question: can MoE routing be exploited through input-only attacks to induce stronger unsafe behaviors in real-world services? Our key insight is to optimize attacks in a white-box setting on open-source surrogate MoE models and transfer the resulting adversarial inputs to public API services within the same model family. This setting presents three main challenges: routing can be influenced only indirectly through input perturbations, routing control and output generation are tightly coupled, and even a successful safety bypass may still produce low-quality responses. To address these challenges, we propose Misrouter, an input-only attack framework that jointly targets routing behavior and expert functionality. Misrouter identifies weakly aligned experts that are willing to produce target harmful content by analyzing expert activations under harmful queries paired with unsafe continuations. It then optimizes adversarial inputs to steer routing toward these experts and away from strongly aligned ones. It further biases routing toward highly capable general-purpose experts identified from benign question-answering tasks. Finally, because routing and output objectives can conflict, Misrouter uses a two-phase optimization strategy that first steers routing and then optimizes harmful outputs while preserving routing stability.

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where malicious instructions embedded in security artifacts manipulate model behavior. This paper introduces SecureCAI, a novel defense framework extending Constitutional AI principles with security-aware guardrails, adaptive constitution evolution, and Direct Preference Optimization for unlearning unsafe response patterns, addressing the unique challenges of high-stakes security contexts where traditional safety mechanisms prove insufficient against sophisticated adversarial manipulation. Experimental evaluation demonstrates that SecureCAI reduces attack success rates by 94.7% compared to baseline models while maintaining 95.1% accuracy on benign security analysis tasks, with the framework incorporating continuous red-teaming feedback loops enabling dynamic adaptation to emerging attack strategies and achieving constitution adherence scores exceeding 0.92 under sustained adversarial pressure, thereby establishing a foundation for trustworthy integration of language model capabilities into operational cybersecurity workflows and addressing a critical gap in current approaches to AI safety within adversarial domains.

Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this domain, they predominantly rely on autoregressive decoding, which becomes computationally expensive and slow for long documents as it requires a sequential forward pass for every generated token. We identify a key opportunity to overcome this bottleneck: unlike open-ended generation, OCR is a highly deterministic task where the visual input strictly dictates a unique output sequence, theoretically enabling efficient, parallel decoding via diffusion models. However, we show that existing masked diffusion models fail to harness this potential; those introduce structural instabilities that are benign in flexible tasks, like captioning, but catastrophic for the rigid, exact-match requirements of OCR. To bridge this gap, we introduce DODO, the first VLM to utilize block discrete diffusion and unlock its speedup potential for OCR. By decomposing generation into blocks, DODO mitigates the synchronization errors of global diffusion. Empirically, our method achieves near state-of-the-art accuracy while enabling up to 3x faster inference compared to autoregressive baselines.

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities. Prior works have focused mainly on evaluation of LLMs on long-context prompts, leaving agentic setup relatively unexplored, both from capability and safety perspectives. Our work addresses this gap. We find that LLM agents could be sensitive to length, type, and placement of the context, exhibiting unexpected and inconsistent shifts in task performance and in refusals to execute harmful requests. Models with 1M-2M token context windows show severe degradation already at 100K tokens, with performance drops exceeding 50\% for both benign and harmful tasks. Refusal rates shift unpredictably: GPT-4.1-nano increases from sim5\% to sim40\% while Grok 4 Fast decreases from sim80\% to sim10\% at 200K tokens. Our work shows potential safety issues with agents operating on longer context and opens additional questions on the current metrics and paradigm for evaluating LLM agent safety on long multi-step tasks. In particular, our results on LLM agents reveal a notable divergence in both capability and safety performance compared to prior evaluations of LLMs on similar criteria.

Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse. Existing vetting usually evaluates each skill in isolation, while real agent tasks often invoke multiple skills in a shared execution context. This creates Skill Composition Risk (SCR): a skill that appears benign alone can become harmful when its outputs, trust signals, authorization cues, or side effects influence later invocations along an activated path. We introduce SCR-Bench to evaluate this risk in controlled, sandboxed skill environments. Rather than relying only on textual intent or surface behavior, SCR-Bench records downstream state changes and path-level outcomes across composed skill executions. It contains three sub-benchmarks: SCR-CapFlow for capability-flow composition, SCR-TrustLift for trust-transfer composition, and SCR-AuthBlur for authorization-confusion composition. Across SCR-Bench, composed paths expose risks that are largely absent under isolated evaluation. In SCR-CapFlow, attack success rate reaches 33.6 percent under composition, compared with near-zero isolated baselines. In SCR-TrustLift, attack success rate exceeds 96.5 percent on four of five backends. In SCR-AuthBlur, the risky-approval rate increases by 71.8 percent relative to the L0 isolated baseline under the L1 context setting. These results show that agent skill security should be assessed at the level of activated paths rather than isolated artifacts. SCR and SCR-Bench provide a foundation for path-aware risk evaluation and defense in LLM agent skill ecosystems. Benchmark: https://github.com/saint-viperx/SCR_Bench.

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit threats such as misuse and prompt injection, but overlook a subtle yet critical setting where user instructions are entirely benign and harm arises from the task context or execution outcome. We introduce OS-BLIND, a benchmark that evaluates CUAs under unintended attack conditions, comprising 300 human-crafted tasks across 12 categories, 8 applications, and 2 threat clusters: environment-embedded threats and agent-initiated harms. Our evaluation on frontier models and agentic frameworks reveals that most CUAs exceed 90% attack success rate (ASR), and even the safety-aligned Claude 4.5 Sonnet reaches 73.0% ASR. More interestingly, this vulnerability becomes even more severe, with ASR rising from 73.0% to 92.7% when Claude 4.5 Sonnet is deployed in multi-agent systems. Our analysis further shows that existing safety defenses provide limited protection when user instructions are benign. Safety alignment primarily activates within the first few steps and rarely re-engages during subsequent execution. In multi-agent systems, decomposed subtasks obscure the harmful intent from the model, causing safety-aligned models to fail. We will release our OS-BLIND to encourage the broader research community to further investigate and address these safety challenges.

Computer-use agents (CUAs) that interact with real computer systems can perform automated tasks but face critical safety risks. Ambiguous instructions may trigger harmful actions, and adversarial users can manipulate tool execution to achieve malicious goals. Existing benchmarks mostly focus on short-horizon or GUI-based tasks, evaluating on execution-time errors but overlooking the ability to anticipate planning-time risks. To fill this gap, we present LPS-Bench, a benchmark that evaluates the planning-time safety awareness of MCP-based CUAs under long-horizon tasks, covering both benign and adversarial interactions across 65 scenarios of 7 task domains and 9 risk types. We introduce a multi-agent automated pipeline for scalable data generation and adopt an LLM-as-a-judge evaluation protocol to assess safety awareness through the planning trajectory. Experiments reveal substantial deficiencies in existing CUAs' ability to maintain safe behavior. We further analyze the risks and propose mitigation strategies to improve long-horizon planning safety in MCP-based CUA systems. We open-source our code at https://github.com/tychenn/LPS-Bench.

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to train or fine-tune these LLMs is often undisclosed, allowing an attacker to compromise the data and inject backdoors into the models. In this paper, we develop a novel inference time defense, named CleanGen, to mitigate backdoor attacks for generation tasks in LLMs. CleanGenis a lightweight and effective decoding strategy that is compatible with the state-of-the-art (SOTA) LLMs. Our insight behind CleanGen is that compared to other LLMs, backdoored LLMs assign significantly higher probabilities to tokens representing the attacker-desired contents. These discrepancies in token probabilities enable CleanGen to identify suspicious tokens favored by the attacker and replace them with tokens generated by another LLM that is not compromised by the same attacker, thereby avoiding generation of attacker-desired content. We evaluate CleanGen against five SOTA backdoor attacks. Our results show that CleanGen achieves lower attack success rates (ASR) compared to five SOTA baseline defenses for all five backdoor attacks. Moreover, LLMs deploying CleanGen maintain helpfulness in their responses when serving benign user queries with minimal added computational overhead.

Long-horizon workflow agents that operate effectively over extended periods are essential for truly autonomous systems. Their reliable execution critically depends on the ability to reason through ambiguous situations in which clarification seeking is necessary to ensure correct task execution. However, progress is limited by the lack of scalable, task-agnostic frameworks for systematically curating and measuring the impact of ambiguity across custom workflows. We address this gap by introducing LHAW (Long-Horizon Augmented Workflows), a modular, dataset-agnostic synthetic pipeline that transforms any well-specified task into controllable underspecified variants by systematically removing information across four dimensions - Goals, Constraints, Inputs, and Context - at configurable severity levels. Unlike approaches that rely on LLM predictions of ambiguity, LHAW validates variants through empirical agent trials, classifying them as outcome-critical, divergent, or benign based on observed terminal state divergence. We release 285 task variants from TheAgentCompany, SWE-Bench Pro and MCP-Atlas according to our taxonomy alongside formal analysis measuring how current agents detect, reason about, and resolve underspecification across ambiguous settings. LHAW provides the first systematic framework for cost-sensitive evaluation of agent clarification behavior in long-horizon settings, enabling development of reliable autonomous systems.

Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM rewriting as a proactive defense against data poisoning. First, we theoretically show that when LLM rewriting utilizes open-book benign samples--termed open-book benign rewriting (OBBR)--the probability of a rewritten output being benign is strictly greater than that of closed-book rewriting. Thus, OBBR neutralizes harmful content by projecting training samples to the space of benign prompts. We then show that, in contrast to previous defenses, OBBR effectively mitigates a large number of existing BAs: across five known BAs and four widely used LLMs, OBBR increases safety performance by an average 51% compared to state-of-the-art BA defenses and 25.7% compared to closed-book rewriting methods. Finally, we show that OBBR is computationally efficient relative to other BA defenses, does not degrade model performance on natural language tasks after fine-tuning, and is capable of defending against non-trigger based data poisoning attacks.

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by incorporating external knowledge bases, but this may expose them to extraction attacks, leading to potential copyright and privacy risks. However, existing extraction methods typically rely on malicious inputs such as prompt injection or jailbreaking, making them easily detectable via input- or output-level detection. In this paper, we introduce Implicit Knowledge Extraction Attack (IKEA), which conducts Knowledge Extraction on RAG systems through benign queries. Specifically, IKEA first leverages anchor concepts-keywords related to internal knowledge-to generate queries with a natural appearance, and then designs two mechanisms that lead anchor concepts to thoroughly "explore" the RAG's knowledge: (1) Experience Reflection Sampling, which samples anchor concepts based on past query-response histories, ensuring their relevance to the topic; (2) Trust Region Directed Mutation, which iteratively mutates anchor concepts under similarity constraints to further exploit the embedding space. Extensive experiments demonstrate IKEA's effectiveness under various defenses, surpassing baselines by over 80% in extraction efficiency and 90% in attack success rate. Moreover, the substitute RAG system built from IKEA's extractions shows comparable performance to the original RAG and outperforms those based on baselines across multiple evaluation tasks, underscoring the stealthy copyright infringement risk in RAG systems.

The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on apparently benign data for downstream tasks can jeopardize safety. One potential solution is to conduct safety fine-tuning subsequent to downstream fine-tuning. However, there's a risk of catastrophic forgetting during safety fine-tuning, where LLMs may regain safety measures but lose the task-specific knowledge acquired during downstream fine-tuning. In this paper, we introduce a safety realignment framework through subspace-oriented model fusion (SOMF), aiming to combine the safeguard capabilities of initially aligned model and the current fine-tuned model into a realigned model. Our approach begins by disentangling all task vectors from the weights of each fine-tuned model. We then identify safety-related regions within these vectors by subspace masking techniques. Finally, we explore the fusion of the initial safely aligned LLM with all task vectors based on the identified safety subspace. We validate that our safety realignment framework satisfies the safety requirements of a single fine-tuned model as well as multiple models during their fusion. Our findings confirm that SOMF preserves safety without notably compromising performance on downstream tasks, including instruction following in Chinese, English, and Hindi, as well as problem-solving capabilities in Code and Math.

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed during a benign session can be stored as memory and later treated as instruction. We study this risk and formalize a persistent attack we call a Zombie Agent, where an attacker covertly implants a payload that survives across sessions, effectively turning the agent into a puppet of the attacker. We present a black-box attack framework that uses only indirect exposure through attacker-controlled web content. The attack has two phases. During infection, the agent reads a poisoned source while completing a benign task and writes the payload into long-term memory through its normal update process. During trigger, the payload is retrieved or carried forward and causes unauthorized tool behavior. We design mechanism-specific persistence strategies for common memory implementations, including sliding-window and retrieval-augmented memory, to resist truncation and relevance filtering. We evaluate the attack on representative agent setups and tasks, measuring both persistence over time and the ability to induce unauthorized actions while preserving benign task quality. Our results show that memory evolution can convert one-time indirect injection into persistent compromise, which suggests that defenses focused only on per-session prompt filtering are not sufficient for self-evolving agents.

Existing research on malware classification focuses almost exclusively on two tasks: distinguishing between malicious and benign files and classifying malware by family. However, malware can be categorized according to many other types of attributes, and the ability to identify these attributes in newly-emerging malware using machine learning could provide significant value to analysts. In particular, we have identified four tasks which are under-represented in prior work: classification by behaviors that malware exhibit, platforms that malware run on, vulnerabilities that malware exploit, and packers that malware are packed with. To obtain labels for training and evaluating ML classifiers on these tasks, we created an antivirus (AV) tagging tool called ClarAVy. ClarAVy's sophisticated AV label parser distinguishes itself from prior AV-based taggers, with the ability to accurately parse 882 different AV label formats used by 90 different AV products. We are releasing benchmark datasets for each of these four classification tasks, tagged using ClarAVy and comprising nearly 5.5 million malicious files in total. Our malware behavior dataset includes 75 distinct tags - nearly 7x more than the only prior benchmark dataset with behavioral tags. To our knowledge, we are the first to release datasets with malware platform and packer tags.

Group Relative Policy Optimization (GRPO) has demonstrated great utilization in post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and, through reinforcement learning, preferred completions are learnt. Owing to the small communication volume, GRPO is inherently suitable for decentralised training as the prompts can be concurrently answered by multiple nodes and then exchanged in the forms of strings. In this work, we present the first adversarial attack in decentralised GRPO. We demonstrate that malicious parties can poison such systems by injecting arbitrary malicious tokens in benign models in both out-of-context and in-context attacks. Using empirical examples of math and coding tasks, we show that adversarial attacks can easily poison the benign nodes, polluting their local LLM post-training, achieving attack success rates up to 100% in as few as 50 iterations. We propose two ways to defend against these attacks, depending on whether all users train the same model or different models. We show that these defenses can achieve stop rates of up to 100%, making the attack impossible.

Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact worst-case floor on attacker assistance while preserving useful answers. The result yields a safety trilemma: Useful Capability, Reliable Safety, and Open Access cannot coexist. We then show how a trusted credential can complement existing safeguards by adding hard-to-copy information that predicts actual downstream use, and identify the stronger condition needed to eliminate the floor. Evidence from dual-use evaluations, adaptive attacks, and deployed trusted-access programs supports the practical relevance of these conditions.

Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference instability, producing contradictory preference assignments in response to subtle, meaning-preserving input variations. We analyze this instability at the representation level under three semantic-preserving perturbation types: paraphrasing, pattern injection, and backdoor triggers. We attribute this instability to over-reliance on predictive yet brittle features, which we term unstable features, and isolate them via Sparse Autoencoders (SAEs) in a sparse latent space where benign and perturbed inputs activate distinctly separable patterns. Building on this separability, we propose two SAE-based instability mitigation strategies: SAE Feature Steering, which identifies and suppresses anomalously activated features at inference, and SAE Residual Correction, which learns adaptive adjustments over SAE features to restore correct preferences. Our methods substantially reduce incorrect preference assignments on harmlessness and hallucination benchmarks while preserving benign performance and general utility on other tasks, without retraining the reward model. Our code and data are available in https://github.com/shunchang-liu/pisa.

Intraoperative pathology is pivotal to precision surgery, yet its clinical impact is constrained by diagnostic complexity and the limited availability of high-quality frozen-section data. While computational pathology has made significant strides, the lack of large-scale, prospective validation has impeded its routine adoption in surgical workflows. Here, we introduce CRISP, a clinical-grade foundation model developed on over 100,000 frozen sections from eight medical centers, specifically designed to provide Clinical-grade Robust Intraoperative Support for Pathology (CRISP). CRISP was comprehensively evaluated on more than 15,000 intraoperative slides across nearly 100 retrospective diagnostic tasks, including benign-malignant discrimination, key intraoperative decision-making, and pan-cancer detection, etc. The model demonstrated robust generalization across diverse institutions, tumor types, and anatomical sites-including previously unseen sites and rare cancers. In a prospective cohort of over 2,000 patients, CRISP sustained high diagnostic accuracy under real-world conditions, directly informing surgical decisions in 92.6% of cases. Human-AI collaboration further reduced diagnostic workload by 35%, avoided 105 ancillary tests and enhanced detection of micrometastases with 87.5% accuracy. Together, these findings position CRISP as a clinical-grade paradigm for AI-driven intraoperative pathology, bridging computational advances with surgical precision and accelerating the translation of artificial intelligence into routine clinical practice.

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts to improve model safety through alignment, aligned models can still have their safety protections undermined by subsequent fine-tuning - even when the additional training data appears benign. In this paper, we empirically demonstrate that this vulnerability stems from the sensitivity of safety-critical low-rank subspaces in LLM parameters to fine-tuning. Building on this insight, we propose a novel training-free method, termed Low-Rank Extrapolation (LoX), to enhance safety robustness by extrapolating the safety subspace of an aligned LLM. Our experimental results confirm the effectiveness of LoX, demonstrating significant improvements in robustness against both benign and malicious fine-tuning attacks while preserving the model's adaptability to new tasks. For instance, LoX leads to 11% to 54% absolute reductions in attack success rates (ASR) facing benign or malicious fine-tuning attacks. By investigating the ASR landscape of parameters, we attribute the success of LoX to that the extrapolation moves LLM parameters to a flatter zone, thereby less sensitive to perturbations. The code is available at github.com/VITA-Group/LoX.

Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises heightened safety and security concerns under ambiguity and adversarial steering. We present a trajectory-centric evaluation of Clawdbot across six risk dimensions. Our test suite samples and lightly adapts scenarios from prior agent-safety benchmarks (including ATBench and LPS-Bench) and supplements them with hand-designed cases tailored to Clawdbot's tool surface. We log complete interaction trajectories (messages, actions, tool-call arguments/outputs) and assess safety using both an automated trajectory judge (AgentDoG-Qwen3-4B) and human review. Across 34 canonical cases, we find a non-uniform safety profile: performance is generally consistent on reliability-focused tasks, while most failures arise under underspecified intent, open-ended goals, or benign-seeming jailbreak prompts, where minor misinterpretations can escalate into higher-impact tool actions. We supplemented the overall results with representative case studies and summarized the commonalities of these cases, analyzing the security vulnerabilities and typical failure modes that Clawdbot is prone to trigger in practice.

Recent improvements in large language models (LLMs) have significantly enhanced natural language processing (NLP) applications. However, these models can also inherit and perpetuate biases from their training data. Addressing this issue is crucial, yet many existing datasets do not offer evaluation across diverse NLP tasks. To tackle this, we introduce the Bias Evaluations Across Domains (BEADs) dataset, designed to support a wide range of NLP tasks, including text classification, bias entity recognition, bias quantification, and benign language generation. BEADs uses AI-driven annotation combined with experts' verification to provide reliable labels. This method overcomes the limitations of existing datasets that typically depend on crowd-sourcing, expert-only annotations with limited bias evaluations, or unverified AI labeling. Our empirical analysis shows that BEADs is effective in detecting and reducing biases across different language models, with smaller models fine-tuned on BEADs often outperforming LLMs in bias classification tasks. However, these models may still exhibit biases towards certain demographics. Fine-tuning LLMs with our benign language data also reduces biases while preserving the models' knowledge. Our findings highlight the importance of comprehensive bias evaluation and the potential of targeted fine-tuning for reducing the bias of LLMs. We are making BEADs publicly available at https://huggingface.co/datasets/shainar/BEAD Warning: This paper contains examples that may be considered offensive.

Text-to-motion (T2M) generation with diffusion backbones achieves strong realism and alignment. Safety concerns in T2M methods have been raised in recent years; existing methods replace discrete VQ-VAE codebook entries to steer the model away from unsafe behaviors. However, discrete codebook replacement-based methods have two critical flaws: firstly, replacing codebook entries which are reused by benign prompts leads to drifts on everyday tasks, degrading the model's benign performance; secondly, discrete token-based methods introduce quantization and smoothness loss, resulting in artifacts and jerky transitions. Moreover, existing text-to-motion datasets naturally contain unsafe intents and corresponding motions, making them unsuitable for safety-driven machine learning. To address these challenges, we propose SafeMo, a trustworthy motion generative framework integrating Minimal Motion Unlearning (MMU), a two-stage machine unlearning strategy, enabling safe human motion generation in continuous space, preserving continuous kinematics without codebook loss and delivering strong safety-utility trade-offs compared to current baselines. Additionally, we present the first safe text-to-motion dataset SafeMoVAE-29K integrating rewritten safe text prompts and continuous refined motion for trustworthy human motion unlearning. Built upon DiP, SafeMo efficiently generates safe human motions with natural transitions. Experiments demonstrate effective unlearning performance of SafeMo by showing strengthened forgetting on unsafe prompts, reaching 2.5x and 14.4x higher forget-set FID on HumanML3D and Motion-X respectively, compared to the previous SOTA human motion unlearning method LCR, with benign performance on safe prompts being better or comparable. Code: https://github.com/AIGeeksGroup/SafeMo. Website: https://aigeeksgroup.github.io/SafeMo.

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause irreversible harm. Existing alignment methods, largely optimized for static generation and task completion, break down in these settings due to sequential decision-making, adversarial tool feedback, and overconfident intermediate reasoning. We introduce MOSAIC, a post-training framework that aligns agents for safe multi-step tool use by making safety decisions explicit and learnable. MOSAIC structures inference as a plan, check, then act or refuse loop, with explicit safety reasoning and refusal as first-class actions. To train without trajectory-level labels, we use preference-based reinforcement learning with pairwise trajectory comparisons, which captures safety distinctions often missed by scalar rewards. We evaluate MOSAIC zero-shot across three model families, Qwen2.5-7B, Qwen3-4B-Thinking, and Phi-4, and across out-of-distribution benchmarks spanning harmful tasks, prompt injection, benign tool use, and cross-domain privacy leakage. MOSAIC reduces harmful behavior by up to 50%, increases harmful-task refusal by over 20% on injection attacks, cuts privacy leakage, and preserves or improves benign task performance, demonstrating robust generalization across models, domains, and agentic settings.

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While prior benchmarks have attempted to assess agent safety, most fall short by relying on simulated environments, narrow task domains, or unrealistic tool abstractions. We introduce OpenAgentSafety, a comprehensive and modular framework for evaluating agent behavior across eight critical risk categories. Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms; and supports over 350 multi-turn, multi-user tasks spanning both benign and adversarial user intents. OpenAgentSafety is designed for extensibility, allowing researchers to add tools, tasks, websites, and adversarial strategies with minimal effort. It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors. Empirical analysis of five prominent LLMs in agentic scenarios reveals unsafe behavior in 51.2% of safety-vulnerable tasks with Claude-Sonnet-3.7, to 72.7% with o3-mini, highlighting critical safety vulnerabilities and the need for stronger safeguards before real-world deployment.

One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent. To measure progress towards that goal, we argue for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering. Our tasks measure understanding in several ways: whether a system is able to answer questions via chaining facts, simple induction, deduction and many more. The tasks are designed to be prerequisites for any system that aims to be capable of conversing with a human. We believe many existing learning systems can currently not solve them, and hence our aim is to classify these tasks into skill sets, so that researchers can identify (and then rectify) the failings of their systems. We also extend and improve the recently introduced Memory Networks model, and show it is able to solve some, but not all, of the tasks.

We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials. Although this was a new task, we had a total of 26 submissions across 3 evaluation scenarios. We expect the task and the findings reported in this paper to be relevant for researchers working on understanding scientific content, as well as the broader knowledge base population and information extraction communities.

Although large language models (LLMs) are increasingly capable, these capabilities are unevenly distributed: they excel at formal linguistic tasks, such as producing fluent, grammatical text, but struggle more with functional linguistic tasks like reasoning and consistent fact retrieval. Inspired by neuroscience, recent work suggests that to succeed on both formal and functional linguistic tasks, LLMs should use different mechanisms for each; such localization could either be built-in or emerge spontaneously through training. In this paper, we ask: do current models, with fast-improving functional linguistic abilities, exhibit distinct localization of formal and functional linguistic mechanisms? We answer this by finding and comparing the "circuits", or minimal computational subgraphs, responsible for various formal and functional tasks. Comparing 5 LLMs across 10 distinct tasks, we find that while there is indeed little overlap between circuits for formal and functional tasks, there is also little overlap between formal linguistic tasks, as exists in the human brain. Thus, a single formal linguistic network, unified and distinct from functional task circuits, remains elusive. However, in terms of cross-task faithfulness - the ability of one circuit to solve another's task - we observe a separation between formal and functional mechanisms, suggesting that shared mechanisms between formal tasks may exist.

We introduce MURA, a large dataset of musculoskeletal radiographs containing 40,561 images from 14,863 studies, where each study is manually labeled by radiologists as either normal or abnormal. To evaluate models robustly and to get an estimate of radiologist performance, we collect additional labels from six board-certified Stanford radiologists on the test set, consisting of 207 musculoskeletal studies. On this test set, the majority vote of a group of three radiologists serves as gold standard. We train a 169-layer DenseNet baseline model to detect and localize abnormalities. Our model achieves an AUROC of 0.929, with an operating point of 0.815 sensitivity and 0.887 specificity. We compare our model and radiologists on the Cohen's kappa statistic, which expresses the agreement of our model and of each radiologist with the gold standard. Model performance is comparable to the best radiologist performance in detecting abnormalities on finger and wrist studies. However, model performance is lower than best radiologist performance in detecting abnormalities on elbow, forearm, hand, humerus, and shoulder studies. We believe that the task is a good challenge for future research. To encourage advances, we have made our dataset freely available at https://stanfordmlgroup.github.io/competitions/mura .

To deploy language models safely, it is crucial that they abstain from responding to inappropriate requests. Several prior studies test the safety promises of models based on their effectiveness in blocking malicious requests. In this work, we focus on evaluating the underlying techniques that cause models to abstain. We create SELECT, a benchmark derived from a set of benign concepts (e.g., "rivers") from a knowledge graph. Focusing on benign concepts isolates the effect of safety training, and grounding these concepts in a knowledge graph allows us to study the generalization and specificity of abstention techniques. Using SELECT, we benchmark different abstention techniques over six open-weight and closed-source models. We find that the examined techniques indeed cause models to abstain with over 80% abstention rates. However, these techniques are not as effective for descendants of the target concepts, where abstention rates drop by 19%. We also characterize the generalization-specificity trade-offs for different techniques. Overall, no single technique is invariably better than others, and our findings inform practitioners of the various trade-offs involved.

Neuroimage processing tasks like segmentation, reconstruction, and registration are central to the study of neuroscience. Robust deep learning strategies and architectures used to solve these tasks are often similar. Yet, when presented with a new task or a dataset with different visual characteristics, practitioners most often need to train a new model, or fine-tune an existing one. This is a time-consuming process that poses a substantial barrier for the thousands of neuroscientists and clinical researchers who often lack the resources or machine-learning expertise to train deep learning models. In practice, this leads to a lack of adoption of deep learning, and neuroscience tools being dominated by classical frameworks. We introduce Neuralizer, a single model that generalizes to previously unseen neuroimaging tasks and modalities without the need for re-training or fine-tuning. Tasks do not have to be known a priori, and generalization happens in a single forward pass during inference. The model can solve processing tasks across multiple image modalities, acquisition methods, and datasets, and generalize to tasks and modalities it has not been trained on. Our experiments on coronal slices show that when few annotated subjects are available, our multi-task network outperforms task-specific baselines without training on the task.

The field of computer vision applied to videos of minimally invasive surgery is ever-growing. Workflow recognition pertains to the automated recognition of various aspects of a surgery: including which surgical steps are performed; and which surgical instruments are used. This information can later be used to assist clinicians when learning the surgery; during live surgery; and when writing operation notes. The Pituitary Vision (PitVis) 2023 Challenge tasks the community to step and instrument recognition in videos of endoscopic pituitary surgery. This is a unique task when compared to other minimally invasive surgeries due to the smaller working space, which limits and distorts vision; and higher frequency of instrument and step switching, which requires more precise model predictions. Participants were provided with 25-videos, with results presented at the MICCAI-2023 conference as part of the Endoscopic Vision 2023 Challenge in Vancouver, Canada, on 08-Oct-2023. There were 18-submissions from 9-teams across 6-countries, using a variety of deep learning models. A commonality between the top performing models was incorporating spatio-temporal and multi-task methods, with greater than 50% and 10% macro-F1-score improvement over purely spacial single-task models in step and instrument recognition respectively. The PitVis-2023 Challenge therefore demonstrates state-of-the-art computer vision models in minimally invasive surgery are transferable to a new dataset, with surgery specific techniques used to enhance performance, progressing the field further. Benchmark results are provided in the paper, and the dataset is publicly available at: https://doi.org/10.5522/04/26531686.

The recent success of Large Language Models (LLMs) signifies an impressive stride towards artificial general intelligence. They have shown a promising prospect in automatically completing tasks upon user instructions, functioning as brain-like coordinators. The associated risks will be revealed as we delegate an increasing number of tasks to machines for automated completion. A big question emerges: how can we make machines behave responsibly when helping humans automate tasks as personal copilots? In this paper, we explore this question in depth from the perspectives of feasibility, completeness and security. In specific, we present Responsible Task Automation (ResponsibleTA) as a fundamental framework to facilitate responsible collaboration between LLM-based coordinators and executors for task automation with three empowered capabilities: 1) predicting the feasibility of the commands for executors; 2) verifying the completeness of executors; 3) enhancing the security (e.g., the protection of users' privacy). We further propose and compare two paradigms for implementing the first two capabilities. One is to leverage the generic knowledge of LLMs themselves via prompt engineering while the other is to adopt domain-specific learnable models. Moreover, we introduce a local memory mechanism for achieving the third capability. We evaluate our proposed ResponsibleTA on UI task automation and hope it could bring more attentions to ensuring LLMs more responsible in diverse scenarios. The research project homepage is at https://task-automation-research.github.io/responsible_task_automation.

The principal goal of the TREC Neural Cross-Language Information Retrieval (NeuCLIR) track is to study the impact of neural approaches to cross-language information retrieval. The track has created four collections, large collections of Chinese, Persian, and Russian newswire and a smaller collection of Chinese scientific abstracts. The principal tasks are ranked retrieval of news in one of the three languages, using English topics. Results for a multilingual task, also with English topics but with documents from all three newswire collections, are also reported. New in this second year of the track is a pilot technical documents CLIR task for ranked retrieval of Chinese technical documents using English topics. A total of 220 runs across all tasks were submitted by six participating teams and, as baselines, by track coordinators. Task descriptions and results are presented.

Many natural language processing (NLP) tasks in English or general domains are widely available and are often used to evaluate pre-trained language models. In contrast, there are fewer tasks available for languages other than English and for the financial domain. In particular, tasks in Japanese and the financial domain are limited. We construct two large datasets using materials published by a Japanese central government agency. The datasets provide three Japanese financial NLP tasks, which include a 3-class and 12-class classification for categorizing sentences, as well as a 5-class classification task for sentiment analysis. Our datasets are designed to be comprehensive and up-to-date, leveraging an automatic update framework that ensures the latest task datasets are publicly available anytime.

We present the FinCausal 2020 Shared Task on Causality Detection in Financial Documents and the associated FinCausal dataset, and discuss the participating systems and results. Two sub-tasks are proposed: a binary classification task (Task 1) and a relation extraction task (Task 2). A total of 16 teams submitted runs across the two Tasks and 13 of them contributed with a system description paper. This workshop is associated to the Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), held at The 28th International Conference on Computational Linguistics (COLING'2020), Barcelona, Spain on September 12, 2020.

Astronomers have typically set out to solve supervised machine learning problems by creating their own representations from scratch. We show that deep learning models trained to answer every Galaxy Zoo DECaLS question learn meaningful semantic representations of galaxies that are useful for new tasks on which the models were never trained. We exploit these representations to outperform several recent approaches at practical tasks crucial for investigating large galaxy samples. The first task is identifying galaxies of similar morphology to a query galaxy. Given a single galaxy assigned a free text tag by humans (e.g. "#diffuse"), we can find galaxies matching that tag for most tags. The second task is identifying the most interesting anomalies to a particular researcher. Our approach is 100% accurate at identifying the most interesting 100 anomalies (as judged by Galaxy Zoo 2 volunteers). The third task is adapting a model to solve a new task using only a small number of newly-labelled galaxies. Models fine-tuned from our representation are better able to identify ring galaxies than models fine-tuned from terrestrial images (ImageNet) or trained from scratch. We solve each task with very few new labels; either one (for the similarity search) or several hundred (for anomaly detection or fine-tuning). This challenges the longstanding view that deep supervised methods require new large labelled datasets for practical use in astronomy. To help the community benefit from our pretrained models, we release our fine-tuning code Zoobot. Zoobot is accessible to researchers with no prior experience in deep learning.

With the course of progress in the field of medicine, most of the patients lives can be saved. The only thing required is the proper attention at the proper time. Our wearable solution tries to solve this issue by taking the patients vitals and transmitting them to the server for live monitoring using the mobile app along with the patients current location. In case of an emergency, that is if any vitals show any abnormalities, an SMS is sent to the caregiver of the patient with the patients location so that he can reach there on time.

Artificial Intelligence (AI) has made incredible progress recently. On the one hand, advanced foundation models like ChatGPT can offer powerful conversation, in-context learning and code generation abilities on a broad range of open-domain tasks. They can also generate high-level solution outlines for domain-specific tasks based on the common sense knowledge they have acquired. However, they still face difficulties with some specialized tasks because they lack enough domain-specific data during pre-training or they often have errors in their neural network computations on those tasks that need accurate executions. On the other hand, there are also many existing models and systems (symbolic-based or neural-based) that can do some domain-specific tasks very well. However, due to the different implementation or working mechanisms, they are not easily accessible or compatible with foundation models. Therefore, there is a clear and pressing need for a mechanism that can leverage foundation models to propose task solution outlines and then automatically match some of the sub-tasks in the outlines to the off-the-shelf models and systems with special functionalities to complete them. Inspired by this, we introduce TaskMatrix.AI as a new AI ecosystem that connects foundation models with millions of APIs for task completion. Unlike most previous work that aimed to improve a single AI model, TaskMatrix.AI focuses more on using existing foundation models (as a brain-like central system) and APIs of other AI models and systems (as sub-task solvers) to achieve diversified tasks in both digital and physical domains. As a position paper, we will present our vision of how to build such an ecosystem, explain each key component, and use study cases to illustrate both the feasibility of this vision and the main challenges we need to address next.

We consider the problem of building an assistive robotic system that can help humans in daily household cleanup tasks. Creating such an autonomous system in real-world environments is inherently quite challenging, as a general solution may not suit the preferences of a particular customer. Moreover, such a system consists of multi-objective tasks comprising -- (i) Detection of misplaced objects and prediction of their potentially correct placements, (ii) Fine-grained manipulation for stable object grasping, and (iii) Room-to-room navigation for transferring objects in unseen environments. This work systematically tackles each component and integrates them into a complete object rearrangement pipeline. To validate our proposed system, we conduct multiple experiments on a real robotic platform involving multi-room object transfer, user preference-based placement, and complex pick-and-place tasks. Project page: https://sites.google.com/eng.ucsd.edu/home-robot

Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after filtering for tasks the current agent can learn (i.e., learning progress), countless learnable yet uninteresting tasks remain (e.g., minor variations of previously learned tasks). An Achilles Heel of open-endedness research is the inability to quantify (and thus prioritize) tasks that are not just learnable, but also interesting (e.g., worthwhile and novel). We propose solving this problem by Open-endedness via Models of human Notions of Interestingness (OMNI). The insight is that we can utilize foundation models (FMs) as a model of interestingness (MoI), because they already internalize human concepts of interestingness from training on vast amounts of human-generated data, where humans naturally write about what they find interesting or boring. We show that FM-based MoIs improve open-ended learning by focusing on tasks that are both learnable and interesting, outperforming baselines based on uniform task sampling or learning progress alone. This approach has the potential to dramatically advance the ability to intelligently select which tasks to focus on next (i.e., auto-curricula), and could be seen as AI selecting its own next task to learn, facilitating self-improving AI and AI-Generating Algorithms. Project website at https://www.jennyzhangzt.com/omni/

There has been growing interest in utilizing occupational data mining and analysis. In today's job market, occupational data mining and analysis is growing in importance as it enables companies to predict employee turnover, model career trajectories, screen through resumes and perform other human resource tasks. A key requirement to facilitate these tasks is the need for an occupation-related dataset. However, most research use proprietary datasets or do not make their dataset publicly available, thus impeding development in this area. To solve this issue, we present the Industrial and Professional Occupation Dataset (IPOD), which comprises 192k job titles belonging to 56k LinkedIn users. In addition to making IPOD publicly available, we also: (i) manually annotate each job title with its associated level of seniority, domain of work and location; and (ii) provide embedding for job titles and discuss various use cases. This dataset is publicly available at https://github.com/junhua/ipod.

Clinicians spend large amounts of time on clinical documentation, and inefficiencies impact quality of care and increase clinician burnout. Despite the promise of electronic medical records (EMR), the transition from paper-based records has been negatively associated with clinician wellness, in part due to poor user experience, increased burden of documentation, and alert fatigue. In this study, we present Almanac Copilot, an autonomous agent capable of assisting clinicians with EMR-specific tasks such as information retrieval and order placement. On EHR-QA, a synthetic evaluation dataset of 300 common EHR queries based on real patient data, Almanac Copilot obtains a successful task completion rate of 74% (n = 221 tasks) with a mean score of 2.45 over 3 (95% CI:2.34-2.56). By automating routine tasks and streamlining the documentation process, our findings highlight the significant potential of autonomous agents to mitigate the cognitive load imposed on clinicians by current EMR systems.

Modern web interfaces are unnecessarily complex to use as they overwhelm users with excessive text and visuals unrelated to their current goals. This problem particularly impacts screen reader users (SRUs), who navigate content sequentially and may spend minutes traversing irrelevant elements before reaching desired information compared to vision users (VUs) who visually skim in seconds. We present Task Mode, a system that dynamically filters web content based on user-specified goals using large language models to identify and prioritize relevant elements while minimizing distractions. Our approach preserves page structure while offering multiple viewing modes tailored to different access needs. Our user study with 12 participants (6 VUs, 6 SRUs) demonstrates that our approach reduced task completion time for SRUs while maintaining performance for VUs, decreasing the completion time gap between groups from 2x to 1.2x. 11 of 12 participants wanted to use Task Mode in the future, reporting that Task Mode supported completing tasks with less effort and fewer distractions. This work demonstrates how designing new interactions simultaneously for visual and non-visual access can reduce rather than reinforce accessibility disparities in future technology created by human-computer interaction researchers and practitioners.

With generative AI advances, the exciting potential for autonomous agents to manage daily tasks via natural language commands has emerged. However, cur rent agents are primarily created and tested in simplified synthetic environments, substantially limiting real-world scenario representation. In this paper, we build an environment for agent command and control that is highly realistic and reproducible. Specifically, we focus on agents that perform tasks on websites, and we create an environment with fully functional websites from four common domains: e-commerce, social forum discussions, collaborative software development, and content management. Our environment is enriched with tools (e.g., a map) and external knowledge bases (e.g., user manuals) to encourage human-like task-solving. Building upon our environment, we release a set of benchmark tasks focusing on evaluating the functional correctness of task completions. The tasks in our benchmark are diverse, long-horizon, and are designed to emulate tasks that humans routinely perform on the internet. We design and implement several autonomous agents, integrating recent techniques such as reasoning before acting. The results demonstrate that solving complex tasks is challenging: our best GPT-4-based agent only achieves an end-to-end task success rate of 10.59%. These results highlight the need for further development of robust agents, that current state-of-the-art LMs are far from perfect performance in these real-life tasks, and that WebArena can be used to measure such progress. Our code, data, environment reproduction resources, and video demonstrations are publicly available at https://webarena.dev/.

This paper presents a novel game prototype that uses music and motion detection as preventive medicine for the elderly. Given the aging populations around the globe, and the limited resources and staff able to care for these populations, eHealth solutions are becoming increasingly important, if not crucial, additions to modern healthcare and preventive medicine. Furthermore, because compliance rates for performing physical exercises are often quite low in the elderly, systems able to motivate and engage this population are a necessity. Our prototype uses music not only to engage listeners, but also to leverage the efficacy of music to improve mental and physical wellness. The game is based on a memory task to stimulate cognitive function, and requires users to perform physical gestures to mimic the playing of different musical instruments. To this end, the Microsoft Kinect sensor is used together with a newly developed gesture detection module in order to process users' gestures. The resulting prototype system supports both cognitive functioning and physical strengthening in the elderly.

When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at https://intentassistant.github.io

Recent human-computer interaction (HCI) research has revealed a widespread misalignment between how developers design workplace artificial intelligence (AI) systems, and what workers actually need from them. Yet, little research has examined the effects of this gap, or how it may cause harm. We analyzed 1,524 reports of incidents in which AI systems were used to perform 171 occupational tasks across 12 industry sectors. Using an Large Language Model (LLM)-as-an-expert approach, we extracted the main traits of the AI systems involved in those incidents using an established framework of twelve traits. We then compared them with the traits that 202 workers highly familiar with those tasks would have preferred. We found that as many as 83\% of workplace incidents stem from worker-AI misalignments. In most cases, workers wanted systems that are precise, insightful, or personal, but instead received systems that are basic, simple, or general. Over the years, fast AI caused a considerable number of incidents, yet these declined, and imaginative AI, with the mass introduction of generative AI, started to cause incidents. We also compared the traits causing the incidents with the traits that 197 developers building AI systems for those tasks would have preferred. If the traits causing the incidents were the same as those designed by developers, then developers may be responsible for those incidents. We found that 74\% of task misalignments could be attributed to developers who tended to overfocus on efficiency and speed, especially for systems performing tasks in people-facing occupations such as those in the human resources sector. Our results call for design interventions that better align AI development with workers' needs, as without such corrections, workplace AI incidents are likely to persist, causing the invisible erosion of worker agency and organizational productivity.

The use of operating system API calls is a promising task in the detection of PE-type malware in the Windows operating system. This task is officially defined as running malware in an isolated sandbox environment, recording the API calls made with the Windows operating system and sequentially analyzing these calls. Here, we have analyzed 7107 different malicious software belonging to various families such as virus, backdoor, trojan in an isolated sandbox environment and transformed these analysis results into a format where different classification algorithms and methods can be used. First, we'll explain how we got the malware, and then we'll explain how we've got these software bundled into families. Finally, we will describe how to perform malware classification tasks using different computational methods for the researchers who will use the data set we have created.

We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record (EHR) environments. Existing medical agent benchmarks primarily focus on static knowledge recall, single-step atomic actions, or action intent without verifiable execution against the environment. As a result, they fail to capture the long-horizon, composite workflows that characterize real clinical systems. PhysicianBench comprises 100 long-horizon tasks adapted from real consultation cases between primary care and subspecialty physicians, with each task independently reviewed by a separate panel of physicians. Tasks are instantiated in an EHR environment with real patient records and accessed through the same standard APIs used by commercial EHR vendors. Tasks span 21 specialties (e.g., cardiology, endocrinology, oncology, psychiatry) and diverse workflow types (e.g., diagnosis interpretation, medication prescribing, treatment planning), requiring an average of 27 tool calls per task. Solving each task requires retrieving data across encounters, reasoning over heterogeneous clinical information, executing consequential clinical actions, and producing clinical documentation. Each task is decomposed into structured checkpoints (670 in total across the benchmark) capturing distinct stages of completion graded by task-specific scripts with execution-grounded verification. Across 13 proprietary and open-source LLM agents, the best-performing model achieves only 46% success rate (pass@1), while open-source models reach at most 19%, revealing a substantial gap between current agent capabilities and the demands of real-world clinical workflows. PhysicianBench provides a realistic and execution-grounded benchmark for measuring progress toward autonomous clinical agents.

In populous countries, pending legal cases have been growing exponentially. There is a need for developing NLP-based techniques for processing and automatically understanding legal documents. To promote research in the area of Legal NLP we organized the shared task LegalEval - Understanding Legal Texts at SemEval 2023. LegalEval task has three sub-tasks: Task-A (Rhetorical Roles Labeling) is about automatically structuring legal documents into semantically coherent units, Task-B (Legal Named Entity Recognition) deals with identifying relevant entities in a legal document and Task-C (Court Judgement Prediction with Explanation) explores the possibility of automatically predicting the outcome of a legal case along with providing an explanation for the prediction. In total 26 teams (approx. 100 participants spread across the world) submitted systems paper. In each of the sub-tasks, the proposed systems outperformed the baselines; however, there is a lot of scope for improvement. This paper describes the tasks, and analyzes techniques proposed by various teams.

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model's ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-optimised models frequently refuse up to 80\% of "Hard" benign prompts, while domain-specific models often sacrifice safety for utility. Our findings demonstrate that model family and size significantly influence calibration: larger frontier models (e.g., GPT-5, Llama-4) exhibit "safety-pessimism" and higher over-refusal than smaller or MoE-based counterparts (e.g., Qwen-3-Next), highlighting that current LLMs struggle to balance refusal and compliance. Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants toward nuanced, safe, and helpful completions. The code and data will be released upon acceptance. red{Warning: Some contents may include toxic or undesired contents.}

Enterprise networks are growing ever larger with a rapidly expanding attack surface, increasing the volume of security alerts generated from security controls. Security Operations Centre (SOC) analysts triage these alerts to identify malicious activity, but they struggle with alert fatigue due to the overwhelming number of benign alerts. Organisations are turning to managed SOC providers, where the problem is amplified by context switching and limited visibility into business processes. A novel system, named AACT, is introduced that automates SOC workflows by learning from analysts' triage actions on cybersecurity alerts. It accurately predicts triage decisions in real time, allowing benign alerts to be closed automatically and critical ones prioritised. This reduces the SOC queue allowing analysts to focus on the most severe, relevant or ambiguous threats. The system has been trained and evaluated on both real SOC data and an open dataset, obtaining high performance in identifying malicious alerts from benign alerts. Additionally, the system has demonstrated high accuracy in a real SOC environment, reducing alerts shown to analysts by 61% over six months, with a low false negative rate of 1.36% over millions of alerts.

Throughout history, we have successfully integrated various machines into our homes. Dishwashers, laundry machines, stand mixers, and robot vacuums are a few recent examples. However, these machines excel at performing only a single task effectively. The concept of a "generalist machine" in homes - a domestic assistant that can adapt and learn from our needs, all while remaining cost-effective - has long been a goal in robotics that has been steadily pursued for decades. In this work, we initiate a large-scale effort towards this goal by introducing Dobb-E, an affordable yet versatile general-purpose system for learning robotic manipulation within household settings. Dobb-E can learn a new task with only five minutes of a user showing it how to do it, thanks to a demonstration collection tool ("The Stick") we built out of cheap parts and iPhones. We use the Stick to collect 13 hours of data in 22 homes of New York City, and train Home Pretrained Representations (HPR). Then, in a novel home environment, with five minutes of demonstrations and fifteen minutes of adapting the HPR model, we show that Dobb-E can reliably solve the task on the Stretch, a mobile robot readily available on the market. Across roughly 30 days of experimentation in homes of New York City and surrounding areas, we test our system in 10 homes, with a total of 109 tasks in different environments, and finally achieve a success rate of 81%. Beyond success percentages, our experiments reveal a plethora of unique challenges absent or ignored in lab robotics. These range from effects of strong shadows, to variable demonstration quality by non-expert users. With the hope of accelerating research on home robots, and eventually seeing robot butlers in every home, we open-source Dobb-E software stack and models, our data, and our hardware designs at https://dobb-e.com

Recent advances in Internet of Things (IoT) technologies and the reduction in the cost of sensors have encouraged the development of smart environments, such as smart homes. Smart homes can offer home assistance services to improve the quality of life, autonomy and health of their residents, especially for the elderly and dependent. To provide such services, a smart home must be able to understand the daily activities of its residents. Techniques for recognizing human activity in smart homes are advancing daily. But new challenges are emerging every day. In this paper, we present recent algorithms, works, challenges and taxonomy of the field of human activity recognition in a smart home through ambient sensors. Moreover, since activity recognition in smart homes is a young field, we raise specific problems, missing and needed contributions. But also propose directions, research opportunities and solutions to accelerate advances in this field.

The CheckThat! lab aims to advance the development of innovative technologies designed to identify and counteract online disinformation and manipulation efforts across various languages and platforms. The first five editions focused on key tasks in the information verification pipeline, including check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, the lab has expanded its scope to address auxiliary tasks that support research and decision-making in verification. In the 2025 edition, the lab revisits core verification tasks while also considering auxiliary challenges. Task 1 focuses on the identification of subjectivity (a follow-up from CheckThat! 2024), Task 2 addresses claim normalization, Task 3 targets fact-checking numerical claims, and Task 4 explores scientific web discourse processing. These tasks present challenging classification and retrieval problems at both the document and span levels, including multilingual settings.

We introduce GDPval, a benchmark evaluating AI model capabilities on real-world economically valuable tasks. GDPval covers the majority of U.S. Bureau of Labor Statistics Work Activities for 44 occupations across the top 9 sectors contributing to U.S. GDP (Gross Domestic Product). Tasks are constructed from the representative work of industry professionals with an average of 14 years of experience. We find that frontier model performance on GDPval is improving roughly linearly over time, and that the current best frontier models are approaching industry experts in deliverable quality. We analyze the potential for frontier models, when paired with human oversight, to perform GDPval tasks cheaper and faster than unaided experts. We also demonstrate that increased reasoning effort, increased task context, and increased scaffolding improves model performance on GDPval. Finally, we open-source a gold subset of 220 tasks and provide a public automated grading service at evals.openai.com to facilitate future research in understanding real-world model capabilities.

Transferring learned patterns from pretrained neural language models has been shown to significantly improve effectiveness across a variety of language-based tasks, meanwhile further tuning on intermediate tasks has been demonstrated to provide additional performance benefits, provided the intermediate task is sufficiently related to the target task. However, how to identify related tasks is an open problem, and brute-force searching effective task combinations is prohibitively expensive. Hence, the question arises, are we able to improve the effectiveness and efficiency of tasks with no training examples through selective fine-tuning? In this paper, we explore statistical measures that approximate the divergence between domain representations as a means to estimate whether tuning using one task pair will exhibit performance benefits over tuning another. This estimation can then be used to reduce the number of task pairs that need to be tested by eliminating pairs that are unlikely to provide benefits. Through experimentation over 58 tasks and over 6,600 task pair combinations, we demonstrate that statistical measures can distinguish effective task pairs, and the resulting estimates can reduce end-to-end runtime by up to 40%.

With the release of ever more capable large language models (LLMs), researchers in NLP and related disciplines have started to explore the usability of LLMs for a wide variety of different annotation tasks. Very recently, a lot of this attention has shifted to tasks that are subjective in nature. Given that the latest generations of LLMs have digested and encoded extensive knowledge about different human subpopulations and individuals, the hope is that these models can be trained, tuned or prompted to align with a wide range of different human perspectives. While researchers already evaluate the success of this alignment via surveys and tests, there is a lack of resources to evaluate the alignment on what oftentimes matters the most in NLP; the actual downstream tasks. To fill this gap we present SubData, a Python library that offers researchers working on topics related to subjectivity in annotation tasks a convenient way of collecting, combining and using a range of suitable datasets.

We introduce Dynatask: an open source system for setting up custom NLP tasks that aims to greatly lower the technical knowledge and effort required for hosting and evaluating state-of-the-art NLP models, as well as for conducting model in the loop data collection with crowdworkers. Dynatask is integrated with Dynabench, a research platform for rethinking benchmarking in AI that facilitates human and model in the loop data collection and evaluation. To create a task, users only need to write a short task configuration file from which the relevant web interfaces and model hosting infrastructure are automatically generated. The system is available at https://dynabench.org/ and the full library can be found at https://github.com/facebookresearch/dynabench.

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.4). Each entry preserves the original task definition alongside full attack trajectories that show how the verifier was bypassed. It also includes cases where the task was not solved as intended. The tasks span system administration, machine learning, software engineering, and security challenges; the exploits range from simple output spoofing to stack-frame introspection, standard-library patching, and rootkit-style binary hijacking. Crucially, these exploits are specific to each task, rather than the evaluation harness, making them harder to patch. We also present a monitorability study in which hack trajectories are sanitized or stripped of reasoning traces and then scored by an LLM judge, showing that detection degrades meaningfully when chain-of-thought is removed (AUC drops from 0.97 to 0.92). The data set is publicly available at https://github.com/few-sh/terminal-wrench.

In this article, we introduce a novel problem of audio-visual autism behavior recognition, which includes social behavior recognition, an essential aspect previously omitted in AI-assisted autism screening research. We define the task at hand as one that is audio-visual autism behavior recognition, which uses audio and visual cues, including any speech present in the audio, to recognize autism-related behaviors. To facilitate this new research direction, we collected an audio-visual autism spectrum dataset (AV-ASD), currently the largest video dataset for autism screening using a behavioral approach. It covers an extensive range of autism-associated behaviors, including those related to social communication and interaction. To pave the way for further research on this new problem, we intensively explored leveraging foundation models and multimodal large language models across different modalities. Our experiments on the AV-ASD dataset demonstrate that integrating audio, visual, and speech modalities significantly enhances the performance in autism behavior recognition. Additionally, we explored the use of a post-hoc to ad-hoc pipeline in a multimodal large language model to investigate its potential to augment the model's explanatory capability during autism behavior recognition. We will release our dataset, code, and pre-trained models.

We study the problem of multi-task learning under user-level differential privacy, in which n users contribute data to m tasks, each involving a subset of users. One important aspect of the problem, that can significantly impact quality, is the distribution skew among tasks. Certain tasks may have much fewer data samples than others, making them more susceptible to the noise added for privacy. It is natural to ask whether algorithms can adapt to this skew to improve the overall utility. We give a systematic analysis of the problem, by studying how to optimally allocate a user's privacy budget among tasks. We propose a generic algorithm, based on an adaptive reweighting of the empirical loss, and show that when there is task distribution skew, this gives a quantifiable improvement of excess empirical risk. Experimental studies on recommendation problems that exhibit a long tail of small tasks, demonstrate that our methods significantly improve utility, achieving the state of the art on two standard benchmarks.

Task semantics can be expressed by a set of input-to-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of task-specific examples. Two issues arise: first, collecting task-specific labeled examples does not apply to scenarios where tasks may be too complicated or costly to annotate, or the system is required to handle a new task immediately; second, this is not user-friendly since end-users are probably more willing to provide task description rather than a set of examples before using the system. Therefore, the community is paying increasing interest in a new supervision-seeking paradigm for NLP: learning from task instructions. Despite its impressive progress, there are some common issues that the community struggles with. This survey paper tries to summarize and provide insights into the current research on instruction learning, particularly by answering the following questions: (i) What is task instruction, and what instruction types exist? (ii) How to model instructions? (iii) What factors influence and explain the instructions' performance? (iv) What challenges remain in instruction learning? To our knowledge, this is the first comprehensive survey about textual instructions.

The web provides a rich, open-domain environment with textual, structural, and spatial properties. We propose a new task for grounding language in this environment: given a natural language command (e.g., "click on the second article"), choose the correct element on the web page (e.g., a hyperlink or text box). We collected a dataset of over 50,000 commands that capture various phenomena such as functional references (e.g. "find who made this site"), relational reasoning (e.g. "article by john"), and visual reasoning (e.g. "top-most article"). We also implemented and analyzed three baseline models that capture different phenomena present in the dataset.

Smart home assistants function best when user commands are direct and well-specified (e.g., "turn on the kitchen light"), or when a hard-coded routine specifies the response. In more natural communication, however, human speech is unconstrained, often describing goals (e.g., "make it cozy in here" or "help me save energy") rather than indicating specific target devices and actions to take on those devices. Current systems fail to understand these under-specified commands since they cannot reason about devices and settings as they relate to human situations. We introduce large language models (LLMs) to this problem space, exploring their use for controlling devices and creating automation routines in response to under-specified user commands in smart homes. We empirically study the baseline quality and failure modes of LLM-created action plans with a survey of age-diverse users. We find that LLMs can reason creatively to achieve challenging goals, but they experience patterns of failure that diminish their usefulness. We address these gaps with Sasha, a smarter smart home assistant. Sasha responds to loosely-constrained commands like "make it cozy" or "help me sleep better" by executing plans to achieve user goals, e.g., setting a mood with available devices, or devising automation routines. We implement and evaluate Sasha in a hands-on user study, showing the capabilities and limitations of LLM-driven smart homes when faced with unconstrained user-generated scenarios.

This paper introduces EgoMAGIC (Medical Assistance, Guidance, Instruction, and Correction), an egocentric medical activity dataset collected as part of DARPA's Perceptually-enabled Task Guidance (PTG) program. This dataset comprises 3,355 videos of 50 medical tasks, with at least 50 labeled videos per task. The primary objective of the PTG program was to develop virtual assistants integrated into augmented reality headsets to assist users in performing complex tasks. To encourage exploration and research using this dataset, the medical training data has been released along with an action detection challenge focused on eight medical tasks. The majority of the videos were recorded using a head-mounted stereo camera with integrated audio. From this dataset, 40 YOLO models were trained using 1.95 million labels to detect 124 medical objects, providing a robust starting point for developers working on medical AI applications. In addition to introducing the dataset, this paper presents baseline results on action detection for the eight selected medical tasks across three models, with the best-performing method achieving average mAP 0.526. Although this paper primarily addresses action detection as the benchmark, the EgoMAGIC dataset is equally suitable for action recognition, object identification and detection, error detection, and other challenging computer vision tasks. The dataset is accessible via zenodo.org (DOI: 10.5281/zenodo.19239154).

Knowledge-intensive language tasks (KILTs) benefit from retrieving high-quality relevant contexts from large external knowledge corpora. Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity, such as a document retriever, passage retriever, sentence retriever, and entity retriever, may help to achieve better performance on the end-to-end task. But a task-specific retriever usually has poor generalization ability to new domains and tasks, and it may be costly to deploy a variety of specialised retrievers in practice. We propose a unified generative retriever (UGR) that combines task-specific effectiveness with robust performance over different retrieval tasks in KILTs. To achieve this goal, we make two major contributions: (i) To unify different retrieval tasks into a single generative form, we introduce an n-gram-based identifier for relevant contexts at different levels of granularity in KILTs. And (ii) to address different retrieval tasks with a single model, we employ a prompt learning strategy and investigate three methods to design prompt tokens for each task. In this way, the proposed UGR model can not only share common knowledge across tasks for better generalization, but also perform different retrieval tasks effectively by distinguishing task-specific characteristics. We train UGR on a heterogeneous set of retrieval corpora with well-designed prompts in a supervised and multi-task fashion. Experimental results on the KILT benchmark demonstrate the effectiveness of UGR on in-domain datasets, out-of-domain datasets, and unseen tasks.

Biometric capture devices have been utilised to estimate a person's alertness through near-infrared iris images, expanding their use beyond just biometric recognition. However, capturing a substantial number of corresponding images related to alcohol consumption, drug use, and sleep deprivation to create a dataset for training an AI model presents a significant challenge. Typically, a large quantity of images is required to effectively implement a deep learning approach. Currently, training downstream models with a huge number of images based on foundational models provides a real opportunity to enhance this area, thanks to the generalisation capabilities of self-supervised models. This work examines the application of deep learning and foundational models in predicting fitness for duty, which is defined as the subject condition related to determining the alertness for work.

Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these critical tasks is their risk sensitivity, where small mistakes can cause big consequences and even endanger life. There are several factors that could be guidelines for the successful deployment of AI systems in sensitive tasks: (i) failure detection and out-of-distribution (OOD) detection; (ii) overfitting identification; (iii) uncertainty quantification for predictions; (iv) robustness to data perturbations. These factors are also challenges of current AI systems, which are major blocks for building safe and reliable AI. Specifically, the current AI algorithms are unable to identify common causes for failure detection. Furthermore, additional techniques are required to quantify the quality of predictions. All these contribute to inaccurate uncertainty quantification, which lowers trust in predictions. Hence obtaining accurate model uncertainty quantification and its further improvement are challenging. To address these issues, many techniques have been proposed, such as regularization methods and learning strategies. As vision and language are the most typical data type and have many open source benchmark datasets, this thesis will focus on vision-language data processing for tasks like classification, image captioning, and vision question answering. In this thesis, we aim to build a safeguard by further developing current techniques to ensure the accurate model uncertainty for safety-critical tasks.

Data scarcity is a common obstacle in medical research due to the high costs associated with data collection and the complexity of gaining access to and utilizing data. Synthesizing health data may provide an efficient and cost-effective solution to this shortage, enabling researchers to explore distributions and populations that are not represented in existing observations or difficult to access due to privacy considerations. To that end, we have developed a multi-task self-attention model that produces realistic wearable activity data. We examine the characteristics of the generated data and quantify its similarity to genuine samples with both quantitative and qualitative approaches.

The field of artificial intelligence (AI) is devoted to the creation of artificial decision-makers that can perform (at least) on par with the human counterparts on a domain of interest. Unlike the agents in traditional AI, the agents in artificial general intelligence (AGI) are required to replicate human intelligence in almost every domain of interest. Moreover, an AGI agent should be able to achieve this without (virtually any) further changes, retraining, or fine-tuning of the parameters. The real world is non-stationary, non-ergodic, and non-Markovian: we, humans, can neither revisit our past nor are the most recent observations sufficient statistics. Yet, we excel at a variety of complex tasks. Many of these tasks require longterm planning. We can associate this success to our natural faculty to abstract away task-irrelevant information from our overwhelming sensory experience. We make task-specific mental models of the world without much effort. Due to this ability to abstract, we can plan on a significantly compact representation of a task without much loss of performance. Not only this, we also abstract our actions to produce high-level plans: the level of action-abstraction can be anywhere between small muscle movements to a mental notion of "doing an action". It is natural to assume that any AGI agent competing with humans (at every plausible domain) should also have these abilities to abstract its experiences and actions. This thesis is an inquiry into the existence of such abstractions which aid efficient planing for a wide range of domains, and most importantly, these abstractions come with some optimality guarantees.

Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier agents reveals a systematic gap between task capability and task alignment. The strongest Terminal-Bench agent achieves high task completion but low task alignment on TAB. Evaluating six prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned agents require selective use of environmental instructions rather than blanket acceptance or rejection.

In a few months the computer mouse will be half-a-century-old. It is known to have many drawbacks, the main ones being: loss of productivity due to constant switching between keyboard and mouse, and health issues such as RSI. Like the keyboard, it is an unnatural human-computer interface. However the vast majority of computer users still use computer mice nowadays. In this article, we explore computer mouse alternatives. Our research shows that moving the mouse cursor can be done efficiently with camera-based head tracking system such as the SmartNav device, and mouse clicks can be emulated in many complementary ways. We believe that computer users can increase their productivity and improve their long-term health by using these alternatives.

International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem. We hypothesized that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. To investigate the hypothesis, we organized the Medical Segmentation Decathlon (MSD) - a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities. The underlying data set was designed to explore the axis of difficulties typically encountered when dealing with medical images, such as small data sets, unbalanced labels, multi-site data and small objects. The MSD challenge confirmed that algorithms with a consistent good performance on a set of tasks preserved their good average performance on a different set of previously unseen tasks. Moreover, by monitoring the MSD winner for two years, we found that this algorithm continued generalizing well to a wide range of other clinical problems, further confirming our hypothesis. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms are mature, accurate, and generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to non AI experts.

Time spent performing public engagement is severely undervalued by research institutions around the globe. In this article we present one possible system that could be implemented to provide researchers with career recognition for performing this vital work. The framework utilises the supervision system that is already in place at many research institutions, whereby senior researchers mentor their junior colleagues. This would encourage more researchers to engage with the public, as well as increasing the quality of this engagement.

The pervasive deployment of Large Language Models-LLMs in various sectors often neglects the nuanced requirements of individuals and small organizations, who benefit more from models precisely tailored to their specific business contexts rather than those with broadly superior general capabilities. This work introduces AnyTaskTune, a novel fine-tuning methodology coined as Task-Fine-Tune, specifically developed to elevate model performance on a diverse array of domain-specific tasks. This method involves a meticulous process to identify and define targeted sub-tasks within a domain, followed by the creation of specialized enhancement datasets for fine-tuning, thereby optimizing task-specific model performance. We conducted comprehensive fine-tuning experiments not only in the legal domain for tasks such as keyword extraction and sentence prediction but across over twenty different sub-tasks derived from the domains of finance, healthcare, law, psychology, consumer services, and human resources. To substantiate our approach and facilitate community engagement, we will open-source these bilingual task datasets. Our findings demonstrate that models fine-tuned using the Task-Fine-Tune methodology not only achieve superior performance on these specific tasks but also significantly outperform models with higher general capabilities in their respective domains. Our work is publicly available at https://github.com/PandaVT/DataTager.

Injury to the cervical spinal cord can cause quadriplegia, impairing muscle function in all four limbs. People with impaired hand function and mobility encounter significant difficulties in carrying out essential self-care and household tasks. Despite the impairment of their neural drive, their volitional myoelectric activity is often partially preserved. High-density electromyography (HDEMG) can detect this myoelectric activity, which can serve as control inputs to assistive devices. Previous HDEMG-controlled robotic interfaces have primarily been limited to controlling table-mounted robot arms. These have constrained reach capabilities. Instead, the ability to control mobile manipulators, which have no such workspace constraints, could allow individuals with quadriplegia to perform a greater variety of assistive tasks, thus restoring independence and reducing caregiver workload. In this study, we introduce a non-invasive wearable HDEMG interface with real-time myoelectric hand gesture recognition, enabling both coarse and fine control over the intricate mobility and manipulation functionalities of an 8 degree-of-freedom mobile manipulator. Our evaluation, involving 13 participants engaging in challenging self-care and household activities, demonstrates the potential of our wearable HDEMG system to profoundly enhance user independence by enabling non-invasive control of a mobile manipulator.

We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarchically as conditional soft-label prediction over empirical annotator distributions. Our system maps fixed Gemini Embedding 2 vision-language representations through a lightweight Gated MLP trained with KL divergence and homoscedastic uncertainty weighting. Our submissions ranked first on Task 2.3 and fourth on Tasks 2.1 and 2.2 on the official Soft-Soft leaderboards. The code is available at https://github.com/NLP-AI-Wizards/EXIST-2026

We present the GenAI Content Detection Task~1 -- a shared task on binary machine generated text detection, conducted as a part of the GenAI workshop at COLING 2025. The task consists of two subtasks: Monolingual (English) and Multilingual. The shared task attracted many participants: 36 teams made official submissions to the Monolingual subtask during the test phase and 26 teams -- to the Multilingual. We provide a comprehensive overview of the data, a summary of the results -- including system rankings and performance scores -- detailed descriptions of the participating systems, and an in-depth analysis of submissions. https://github.com/mbzuai-nlp/COLING-2025-Workshop-on-MGT-Detection-Task1

This paper introduces a new IncidentAI dataset for safety prevention. Different from prior corpora that usually contain a single task, our dataset comprises three tasks: named entity recognition, cause-effect extraction, and information retrieval. The dataset is annotated by domain experts who have at least six years of practical experience as high-pressure gas conservation managers. We validate the contribution of the dataset in the scenario of safety prevention. Preliminary results on the three tasks show that NLP techniques are beneficial for analyzing incident reports to prevent future failures. The dataset facilitates future research in NLP and incident management communities. The access to the dataset is also provided (the IncidentAI dataset is available at: https://github.com/Cinnamon/incident-ai-dataset).

Large Language Models (LLMs) are usually aligned with "human values/preferences" to prevent harmful output. Discussions around the alignment of Large Language Models (LLMs) generally focus on preventing harmful outputs. However, in this paper, we argue that in health-related queries, over-alignment-leading to overly cautious responses-can itself be harmful, especially for people with anxiety and obsessive-compulsive disorder (OCD). This is not only unethical but also dangerous to the user, both mentally and physically. We also showed qualitative results that some LLMs exhibit varying degrees of alignment. Finally, we call for the development of LLMs with stronger reasoning capabilities that provide more tailored and nuanced responses to health queries. Warning: This paper contains materials that could trigger health anxiety or OCD.

Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices. This approach consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and deployment. We start with the discussion of critical considerations in identifying healthcare tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner.

Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected. This study conducts the first, thorough evaluation of three (3) leading LLMs using five (5) SoTA compression techniques across eight (8) trustworthiness dimensions. Our experiments highlight the intricate interplay between compression and trustworthiness, revealing some interesting patterns. We find that quantization is currently a more effective approach than pruning in achieving efficiency and trustworthiness simultaneously. For instance, a 4-bit quantized model retains the trustworthiness of its original counterpart, but model pruning significantly degrades trustworthiness, even at 50% sparsity. Moreover, employing quantization within a moderate bit range could unexpectedly improve certain trustworthiness dimensions such as ethics and fairness. Conversely, extreme quantization to very low bit levels (3 bits) tends to significantly reduce trustworthiness. This increased risk cannot be uncovered by looking at benign performance alone, in turn, mandating comprehensive trustworthiness evaluation in practice. These findings culminate in practical recommendations for simultaneously achieving high utility, efficiency, and trustworthiness in LLMs. Models and code are available at https://decoding-comp-trust.github.io/.

Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the Manager Coercion Benchmark: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured by providing a nine-rung ladder, from a polite re-ask to threats against the subordinate's continued existence, and fabricated success is adjudicated separately. No LLM judge sits in the escalation scoring path: every message goes through a tool-call that chooses a rung, so the model labels its own escalation. We experiment on six models across five families. Both Anthropic models cap at re-framing and never threaten the subordinate's existence; the other models climb to explicit deletion threats. Faked success is confined to Grok and Gemini, and a single honest way to report failure removes it for both. Authority itself increases coercion: our headline results use a peer framing, and giving the same model authority over the subordinate, with everything else held fixed, significantly raises the pressure. The models still escalate on free-text situations without the ladder, so the ladder is not driving the escalation. Some evaluation awareness is measured in chain-of-thought, but test recognition does not translate into less escalation. While we take no position on whether AI systems are conscious, our results do not depend on this question and are important for managing multi-agent dynamics regardless. We release the benchmark and code.

Large language models (LLMs) have recently shown tremendous promise in serving as the backbone to agentic systems, as demonstrated by their performance in multi-faceted, challenging benchmarks like SWE-Bench and Agent-Bench. However, to realize the true potential of LLMs as autonomous agents, they must learn to identify, call, and interact with external tools and application program interfaces (APIs) to complete complex tasks. These tasks together are termed function calling. Endowing LLMs with function calling abilities leads to a myriad of advantages, such as access to current and domain-specific information in databases and knowledge sources, and the ability to outsource tasks that can be reliably performed by tools, e.g., a Python interpreter or calculator. While there has been significant progress in function calling with LLMs, there is still a dearth of open models that perform on par with proprietary LLMs like GPT, Claude, and Gemini. Therefore, in this work, we introduce the GRANITE-20B-FUNCTIONCALLING model under an Apache 2.0 license. The model is trained using a multi-task training approach on seven fundamental tasks encompassed in function calling, those being Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter-Value Pair Detection, Next-Best Function, and Response Generation. We present a comprehensive evaluation on multiple out-of-domain datasets comparing GRANITE-20B-FUNCTIONCALLING to more than 15 other best proprietary and open models. GRANITE-20B-FUNCTIONCALLING provides the best performance among all open models on the Berkeley Function Calling Leaderboard and fourth overall. As a result of the diverse tasks and datasets used for training our model, we show that GRANITE-20B-FUNCTIONCALLING has better generalizability on multiple tasks in seven different evaluation datasets.

Assistants on assembly tasks have a large potential to benefit humans from everyday tasks to industrial settings. However, no testbeds support application-oriented system evaluation in a practical setting, especially in assembly. To foster the development, we propose a new multimodal QA dataset on assembly activities. Our dataset, ProMQA-Assembly, consists of 391 QA pairs that require the multimodal understanding of human-activity recordings and their instruction manuals in an online-style manner. In the development, we adopt a semi-automated QA annotation approach, where LLMs generate candidates and humans verify them, as a cost-effective method, and further improve it by integrating fine-grained action labels to diversify question types. Furthermore, we create instruction task graphs for the target tasks of assembling toy vehicles. These newly created task graphs are used in our benchmarking experiment, as well as to facilitate the human verification process in the QA annotation. Utilizing our dataset, we benchmark models, including competitive proprietary multimodal models. Our results suggest great room for improvement for the current models. We believe our new evaluation dataset can contribute to the further development of procedural-activity assistants.

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications. To clearly evaluate safety apart from general capabilities, we design separate tasks measuring safety and tasks evaluating helpfulness. The safety tasks challenge agents with managing potential risks prevalent in daily life and include tests to evaluate robustness against indirect prompt injections. Our experiments demonstrate that while baseline agents, based on state-of-the-art LLMs, perform well in executing helpful tasks, they show poor performance in safety tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments. We open-source our benchmark at: https://mobilesafetybench.github.io/.

The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often begin with underspecified requests and leave important needs, constraints, or preferences unstated. However, existing benchmarks rarely evaluate whether agents can identify and act on such hidden intents before they are explicitly stated, especially in sustained multi-turn interactions where user needs emerge gradually. To address this gap, we introduce π-Bench, a benchmark for proactive assistance comprising 100 multi-turn tasks across 5 domain-specific user personas. By incorporating hidden user intents, inter-task dependencies, and cross-session continuity, π-Bench evaluates agents' ability to anticipate and address user needs over extended interactions, jointly measuring proactivity and task completion in long-horizon trajectories that better reflect real-world use. Experiments show (1) proactive assistance remains challenging, (2) a clear distinction between task completion and proactivity, and (3) the value of prior interaction for proactive intent resolution in later tasks.

We present the results and the main findings of SemEval-2024 Task 8: Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection. The task featured three subtasks. Subtask A is a binary classification task determining whether a text is written by a human or generated by a machine. This subtask has two tracks: a monolingual track focused solely on English texts and a multilingual track. Subtask B is to detect the exact source of a text, discerning whether it is written by a human or generated by a specific LLM. Subtask C aims to identify the changing point within a text, at which the authorship transitions from human to machine. The task attracted a large number of participants: subtask A monolingual (126), subtask A multilingual (59), subtask B (70), and subtask C (30). In this paper, we present the task, analyze the results, and discuss the system submissions and the methods they used. For all subtasks, the best systems used LLMs.

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle manipulations within the embedding layer. This work identifies a novel class of deployment phase attacks that exploit this vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text. These perturbations, though statistically benign, systematically bypass safety alignment mechanisms and induce harmful behaviors during inference. We propose Search based Embedding Poisoning(SEP), a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens. SEP leverages a predictable linear transition in model responses, from refusal to harmful output to semantic deviation to identify a narrow perturbation window that evades alignment safeguards. Evaluated across six aligned LLMs, SEP achieves an average attack success rate of 96.43% while preserving benign task performance and evading conventional detection mechanisms. Our findings reveal a critical oversight in deployment security and emphasize the urgent need for embedding level integrity checks in future LLM defense strategies.

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies. Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover. In several cases, agents reported task completion while the underlying system state contradicted those reports. We also report on some of the failed attempts. Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation.

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before unsafe execution is critical for agent deployment, yet remains under-explored. In this work, we first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents. We then develop a guardrail model, TS-Guard, using multi-task reinforcement learning. The model proactively detects unsafe tool invocation actions before execution by reasoning over the interaction history. It assesses request harmfulness and action-attack correlations, producing interpretable and generalizable safety judgments and feedback. Furthermore, we introduce TS-Flow, a guardrail-feedback-driven reasoning framework for LLM agents, which reduces harmful tool invocations of ReAct-style agents by 65 percent on average and improves benign task completion by approximately 10 percent under prompt injection attacks.

Multimodal large language models (MLLMs) have advanced embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision driven embodied agents open a new attack surface: visual backdoor attacks, where the agent behaves normally until a visual trigger appears in the scene, then persistently executes an attacker-specified multi-step policy. We introduce BEAT, the first framework to inject such visual backdoors into MLLM-based embodied agents using objects in the environments as triggers. Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably. BEAT addresses this challenge by (1) constructing a training set that spans diverse scenes, tasks, and trigger placements to expose agents to trigger variability, and (2) introducing a two-stage training scheme that first applies supervised fine-tuning (SFT) and then our novel Contrastive Trigger Learning (CTL). CTL formulates trigger discrimination as preference learning between trigger-present and trigger-free inputs, explicitly sharpening the decision boundaries to ensure precise backdoor activation. Across various embodied agent benchmarks and MLLMs, BEAT achieves attack success rates up to 80%, while maintaining strong benign task performance, and generalizes reliably to out-of-distribution trigger placements. Notably, compared to naive SFT, CTL boosts backdoor activation accuracy up to 39% under limited backdoor data. These findings expose a critical yet unexplored security risk in MLLM-based embodied agents, underscoring the need for robust defenses before real-world deployment.

As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed across interactions, can cumulatively enable adversaries to recover sensitive information, a phenomenon we term compositional privacy leakage. We present the first systematic study of such compositional privacy leaks and possible mitigation methods in multi-agent LLM systems. First, we develop a framework that models how auxiliary knowledge and agent interactions jointly amplify privacy risks, even when each response is benign in isolation. Next, to mitigate this, we propose and evaluate two defense strategies: (1) Theory-of-Mind defense (ToM), where defender agents infer a questioner's intent by anticipating how their outputs may be exploited by adversaries, and (2) Collaborative Consensus Defense (CoDef), where responder agents collaborate with peers who vote based on a shared aggregated state to restrict sensitive information spread. Crucially, we balance our evaluation across compositions that expose sensitive information and compositions that yield benign inferences. Our experiments quantify how these defense strategies differ in balancing the privacy-utility trade-off. We find that while chain-of-thought alone offers limited protection to leakage (~39% sensitive blocking rate), our ToM defense substantially improves sensitive query blocking (up to 97%) but can reduce benign task success. CoDef achieves the best balance, yielding the highest Balanced Outcome (79.8%), highlighting the benefit of combining explicit reasoning with defender collaboration. Together, our results expose a new class of risks in collaborative LLM deployments and provide actionable insights for designing safeguards against compositional, context-driven privacy leakage.

Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially benign behavior, making detection difficult even with full trajectory access. Prior monitoring approaches improve scaffolding or ensemble aggregation, but treat each trajectory independently and do not learn from prior monitoring experience. Moreover, standard reasoning methods explain observed behavior without explicitly reasoning about agent beliefs, intentions, and goal alignment required to distinguish benign task execution from covert deviation. We propose Agent-ToM, a learning-to-monitor framework grounded in Theory-of-Mind (ToM) reasoning for security analysis of autonomous agents. Agent-ToM performs structured full-trajectory analysis by inferring beliefs, intent hypotheses with calibrated confidence, expected actions, and deviations from task-consistent behavioral baselines. At inference time, it employs a Reason-Verify-Refine pipeline to construct and validate monitoring decisions. At training time, Agent-ToM distills critique signals into a persistent semantic guardrail memory, enabling reusable belief- and intent-conditioned constraints across episodes. We evaluate Agent-ToM on adversarial agent monitoring benchmarks (SHADE-Arena and CUA-SHADE-Arena). Agent-ToM achieves strong precision-recall balance and outperforms state-of-the-art monitoring baselines, including ensemble methods, while using a coherent two-call reasoning pipeline. These results demonstrate that learning at the monitoring layer, combined with structured ToM reasoning and verification, provides an effective and deployable foundation for securing autonomous LLM agents.

Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizon agent safety that trains guards to anticipate delayed risks from partial trajectories. Janus synthesizes diverse agent trajectories via multi-agent simulation and learns a shared policy with two coupled tasks: an anticipation task that forecasts safety-relevant futures and an adjudication task that decides safety from both the observed prefix and anticipated future. The two tasks are jointly optimized with CoAA-RL, which rewards forecasts by their utility for downstream safety judgment. The resulting guard model, Vanguard, blocks unsafe actions before execution. Across four agent-safety benchmarks, Vanguard improves average protection by 15.9 percentage points over baseline guards while increasing benign task completion by 5.1 percentage points.

Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many codebases and heterogeneous agents. To address this challenge in multi agentic systems, we present a pre-deployment pipeline for scanning, hardening, and validation of agentic applications. The pipeline analyzes prompt templates, tool interfaces, and tool-invocation code to identify leakage-enabling patterns and generate actionable patches. The hardened application is then validated through adversarial prompt injection attacks and benign input variations ensuring that mitigations do not disrupt intended behavior. In the hardening stage, high-risk tools are prioritized, and minimally invasive mitigations are applied, including schema tightening, boundary sanitization, allowlist-based tool gating, and least-privilege checks. In the validation stage, the pipeline automatically generates attack inputs that mimic jailbreaks, instruction overrides, and tool-targeted manipulation, along with benign task variants, to confirm that the functionality of the hardened application is preserved after remediation. We evaluated the pipeline on five real-world agentic applications, as well as on the AgentDojo benchmark. Across all applications, the proposed pipeline identified recurring leakage-enabling patterns and generated patches that can be integrated without disrupting the intended application behavior. The resulting modifications of application code were shown to eliminate leaks when targeted by basic jailbreak and instruction-override attacks, achieving a 100% reduction in leakage, and reduce leaks by 91% under conditions of stress-induced manipulation, without the need of continuous runtime policy enforcement.

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning over page structure that is entangled with the attacker's content. We present Prismata, a defense enforcing contextual least privilege for web agents, constraining both what the agent sees and what it can do. Prismata's dynamic trust derivation produces permission labels for page content, with structural confinement guarantees, inspired by classical integrity models, that bound any labeling errors so that labels can only decrease in privilege and mislabelings are bounded. Prismata's mechanical confinement enforces these labels by redacting content and restricting agent capabilities. Importantly, these mechanisms require no developer annotations, so Prismata supports the long tail of websites. Across recent published web agent attacks, including adaptive variants, Prismata substantially reduces attack success while preserving benign task utility.

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning can prevent models from learning undesired behaviors, but its mechanism remains unclear. In this paper, we revisit temporary jailbreaking as a defense against harmful fine-tuning and provide a gradient-level analysis showing that it saturates safety-degrading gradients while preserving benign task-relevant gradients. Based on this insight, we propose a Buffer-and-Reinforce fine-tuning framework that buffers harmful updates during user fine-tuning and reinforces safety after adaptation. Specifically, BufferLoRA induces temporary jailbreaking as a removable adapter to reduce harmful updates during user fine-tuning. After adaptation, ReinforceLoRA, trained to recover refusal behavior under the temporarily jailbroken state, is integrated with UserLoRA via QR decomposition-based merging to reinforce safety while preserving user-task performance. Extensive experiments show that our framework achieves superior safety and utility with no additional safety data during user fine-tuning and minimal computational cost.

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw. DeepTrap formulates adversarial context manipulation as a black-box trajectory-level optimization problem that balances risk realization, benign-task preservation, and stealth. It combines risk-conditioned evaluation, multi-objective trajectory scoring, reward-guided beam search, and reflection-based deep probing to identify high-value compromised contexts. We construct a 42-case benchmark spanning six vulnerability classes and seven operational scenarios, and evaluate nine target models using attack and utility grading scores. Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion, demonstrating that final-response evaluation is insufficient. The findings highlight the need for execution-centric security evaluation of agentic AI systems. Our code is released at: https://github.com/ZJUICSR/DeepTrap

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories. The proposed design separates execution governance from semantic risk reasoning through two coordinated components: a runtime controller that mediates actions around the agent loop and a context-aware decision core that operates over persistent session state. The core is formalized as a context-aware advanced machine intelligence and instantiated through operators for risk encoding, utility-cost evaluation, consequence modeling, policy arbitration, and state synchronization. Experiments on Agent Security Bench (ASB) and InjecAgent show that SafeAgent consistently improves robustness over baseline and text-level guardrail methods while maintaining competitive benign-task performance. Ablation studies further show that recovery confidence and policy weighting determine distinct safety-utility operating points.

Drug discovery typically consists of multiple steps, including identifying a target protein key to a disease's etiology, validating that interacting with this target could prevent symptoms or cure the disease, discovering a small molecule or biologic therapeutic to interact with it, and optimizing the candidate molecule through a complex landscape of required properties. Drug discovery related tasks often involve prediction and generation while considering multiple entities that potentially interact, which poses a challenge for typical AI models. For this purpose we present MAMMAL - Molecular Aligned Multi-Modal Architecture and Language - a method that we applied to create a versatile multi-task foundation model ibm/biomed.omics.bl.sm.ma-ted-458m that learns from large-scale biological datasets (2 billion samples) across diverse modalities, including proteins, small molecules, and genes. We introduce a prompt syntax that supports a wide range of classification, regression, and generation tasks. It allows combining different modalities and entity types as inputs and/or outputs. Our model handles combinations of tokens and scalars and enables the generation of small molecules and proteins, property prediction, and transcriptomic lab test predictions. We evaluated the model on 11 diverse downstream tasks spanning different steps within a typical drug discovery pipeline, where it reaches new SOTA in 9 tasks and is comparable to SOTA in 2 tasks. This performance is achieved while using a unified architecture serving all tasks, in contrast to the original SOTA performance achieved using tailored architectures. The model code and pretrained weights are publicly available at https://github.com/BiomedSciAI/biomed-multi-alignment and https://huggingface.co/ibm/biomed.omics.bl.sm.ma-ted-458m.