PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
Paper • 2609.40285 • Published • 22
Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents upvoted a paper about 16 hours ago
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents upvoted a paper about 16 hours ago
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific DiscoveryOrganizations
None yet
upvoted a paper about 4 hours ago
upvoted 5
papers about 16 hours ago
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
Paper • 2609.40325 • Published • 103
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Paper • 2609.40340 • Published • 110
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
Paper • 2609.35432 • Published • 109
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Paper • 2609.39982 • Published • 118
LEGO-Anything: Coding Agents for 3D Scene Reconstruction
Paper • 2609.36380 • Published • 139
upvoted 6
papers about 17 hours ago
Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL
Paper • 2609.32577 • Published • 133
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 142
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Paper • 2609.33757 • Published • 250
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 676
Omni-IO Skills: Harnessing Your Agent Omni-Native
Paper • 2609.31847 • Published • 450
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Paper • 2609.33439 • Published • 569
upvoted a paper 1 day ago
upvoted 3
papers 2 days ago
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
Paper • 2609.30199 • Published • 30
JEPA-Anything: Learning Predictive Models across Different Worlds
Paper • 2609.20800 • Published • 78
Language Models that Play Chess and Explain Their Moves
Paper • 2610.03695 • Published • 36
upvoted 4
papers 4 days ago
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
Paper • 2610.02202 • Published • 13
Decoding Looped Transformers Better for (Almost) Free
Paper • 2610.02185 • Published • 45
AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs
Paper • 2609.31590 • Published • 13
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
Paper • 2609.38147 • Published • 1