Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
Paper
•
2509.09265
•
Published
•
45
Yuqian Fu
Yuqian-Fu
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
28 days ago
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP
Use
updated
a collection
about 1 month ago
SRFT
updated
a collection
about 1 month ago
SRFT
Organizations
None yet
authored
a
paper
about 2 months ago
authored
3
papers
4 months ago
RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
Paper
•
2506.00439
•
Published
•
1
Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation
Paper
•
2503.12854
•
Published
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
Paper
•
2506.19767
•
Published
•
14