SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
Paper
•
2511.06411
•
Published
•
17
Zhi Zheng
zz1358m
·
AI & ML interests
LLM reasoning, Trustworthy LLM, LLM application, Neural combinatorial optimization.
Recent Activity
liked
a model
about 2 months ago
zz1358m/SofT-GRPO-master
updated
a model
about 2 months ago
zz1358m/SofT-GRPO-master
authored
a paper
about 2 months ago
SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via
Gumbel-Reparameterized Soft-Thinking Policy Optimization
Organizations
authored
a
paper
about 2 months ago
authored
3
papers
8 months ago
Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
Paper
•
2501.08603
•
Published
UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems
Paper
•
2407.00312
•
Published
Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification
Paper
•
2505.12348
•
Published