6 papers
Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models
Zongji Yu, Wenshui Luo, Yiliu Sun +4
Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Group Relative Policy Optimizat…
TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization
Peiji Li, Linyang Li, Handa Sun +15
Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration, which is typically framed as a Markov Decision Process and optimize…
Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
Yiliu Sun, Zicheng Zhao, Yang Wei +2
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capability of Large Language Models (LLMs). Current RLVR approaches typically conduct tra…
CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate
Yiliu Sun, Zicheng Zhao, Sheng Wan +1
Nowadays, single Large Language Model (LLM) struggles with critical issues such as hallucination and inadequate reasoning abilities. To mitigate these issues, Multi-Agent Debate (M…
Fast-Slow-Thinking: Complex Task Solving with Large Language Models
Yiliu Sun, Yanfang Zhang, Zicheng Zhao +3
Nowadays, Large Language Models (LLMs) have been gradually employed to solve complex tasks. To face the challenge, task decomposition has become an effective way, which proposes to…
Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning
Yanfang Zhang, Yiliu Sun, Yibing Zhan +3
Recently, increasing attention has been focused on improving the ability of Large Language Models (LLMs) to perform complex reasoning. Advanced methods, such as Chain-of-Thought (C…