Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment
Paper
•
2505.11821
•
Published
•
13
Yimeng Zhang
DamonDemon
AI & ML interests
Computer Vision, Generative AI, Multi-Modality, AI Safety, Efficient AI
Recent Activity
upvoted
a
paper
8 days ago
Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit
Assignment
liked
a Space
about 1 month ago
ByteDance/ID-Patch-SDXL
Organizations
