BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents
Paper • 2606.25556 • Published • 1
Hanyang Wang
ssyhw7
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 months ago
The Detection--Extraction Gap: Models Know the Answer Before They Can Say It upvoted a paper 5 months ago
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement LearningOrganizations
None yet