9 papers
Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
Xueyun Tian, Minghua Ma, Bingbing Xu +6
Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typicall…
Virtual Width Networks
Seed, Baisheng Li, Banggu Wu +115
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…
Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models
Yuhua Jiang, Jiawei Huang, Yufeng Yuan +4
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer f…
Truncated Proximal Policy Optimization
Tiantian Fan, Lingjun Liu, Yu Yue +20
Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-…
PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
Yuhua Jiang, Yuwen Xiong, Yufeng Yuan +5
Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs.…
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Qiying Yu, Zheng Zhang, Ruofei Zhu +32
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details…