arxiv:2504.09772
Can Jin PRO
Can111
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Behavior Knowledge Merge in Reinforced Agentic Models upvoted a paper 3 months ago
M3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark upvoted a paper 5 months ago
EPO: Entropy-regularized Policy Optimization for LLM Agents
Reinforcement Learning Organizations
None yet