AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA Paper • 2608.30556 • Published Aug 31 • 20
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay Paper • 2610.27954 • Published 20 days ago • 37
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data Paper • 2610.37386 • Published 13 days ago • 26
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL Paper • 2610.33512 • Published 16 days ago • 35
Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery Paper • 2610.32195 • Published 17 days ago • 27
RunningTab: Direct Workspace Interaction with Environment-Side Tabs Paper • 2610.10444 • Published Oct 7 • 38
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents Paper • 2610.05140 • Published Oct 4 • 33
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published Sep 30 • 96
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published Sep 30 • 91