Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective
Paper
•
2505.19815
•
Published
•
37
•
2
Junnan Liu
jnanliu
AI & ML interests
NLP, LLM, LLM Reasoning, Agentic AI
Recent Activity
liked
a dataset
16 days ago
Skywork/Skywork-OR1-RL-Data
upvoted
a
paper
16 days ago
CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
liked
a model
20 days ago
moonshotai/Kimi-K2-Base
Organizations
commented
a
paper
2 months ago