When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents
Paper • 2609.32520 • Published • 25
marinaretikof
marinaretik
AI & ML interests
None yet
Recent Activity
upvoted a paper 11 days ago
When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents upvoted a paper 11 days ago
GraphForge: Training Working Agents with Graph-Anchored Workspace SynthesisOrganizations
None yet
upvoted 20
papers 11 days ago
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
Paper • 2609.38923 • Published • 125
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
Paper • 2610.01762 • Published • 237
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Paper • 2610.02826 • Published • 106
Does Learning Protein Folding Generalize to Broader Reasoning?
Paper • 2609.38879 • Published • 64
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
Paper • 2610.05750 • Published • 21
Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
Paper • 2609.37267 • Published • 40
Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy
Paper • 2610.05162 • Published • 62
ALoDLM: Adaptively Looped Diffusion Language Models
Paper • 2610.04198 • Published • 80
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
Paper • 2610.06647 • Published • 154
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Paper • 2610.05608 • Published • 174
StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
Paper • 2610.03799 • Published • 5
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
Paper • 2610.09127 • Published • 24
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Paper • 2610.09832 • Published • 17
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
Paper • 2610.10164 • Published • 8
Recurrent Looped Transformer
Paper • 2610.07591 • Published • 33
UniWAM: Unified World-Action Model
Paper • 2610.02054 • Published • 83
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Paper • 2610.04299 • Published • 85
From Evidence to Action: How Tool-Using Agents Fail
Paper • 2610.07753 • Published • 46
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Paper • 2610.05030 • Published • 55