Entities · Models
SWE-bench Verified
4 articles tagged with this entity.
-
HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness
-
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
-
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
-
Automated Benchmark Auditing for AI Agents and Large Language Models