MASTER: A Multi-Agent System with LLM Specialized MCTS
Paper
•
2501.14304
•
Published
Changwang ZHANG
mLeoKing
·
AI & ML interests
AI Information Retrieval (Retrieval Augmented Generation, Multimodal Retrieval, Search-Recommendation-Advertising) | AI agents (intention recognition, agent framework) | Large AI models (large reasoning models R1/O1)
Organizations
authored
7
papers
4 months ago
OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning
Paper
•
2503.16081
•
Published
•
28
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
Paper
•
2506.02397
•
Published
•
35
TaskCraft: Automated Generation of Agentic Tasks
Paper
•
2506.10055
•
Published
•
32
Scaling Test-time Compute for LLM Agents
Paper
•
2506.12928
•
Published
•
63
OAgents: An Empirical Study of Building Effective Agents
Paper
•
2506.15741
•
Published
•
35
Efficient Agents: Building Effective Agents While Reducing Cost
Paper
•
2508.02694
•
Published
•
86