Cover Image

Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Zhaohui, Ye, Yuxiao, Jiang, Shilei, Hu, Chen, Li, Linjing, Deng, Shihong, Jiang, Daxin
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
by: He, Haoran, et al.
Published: (2025)

Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning
by: Yang, Zhaohui, et al.
Published: (2025)

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
by: Yang, Yuxiao, et al.
Published: (2026)

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
by: Zhang, Yuheng, et al.
Published: (2026)

Structured Role-Aware Policy Optimization for Multimodal Reasoning
by: Jiang, Bingqing, et al.
Published: (2026)

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
by: Mao, Yixiu, et al.
Published: (2026)

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
by: Chen, Haoxuan, et al.
Published: (2026)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
by: Liu, Zeyuan, et al.
Published: (2026)

Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
by: Melo, Luckeciano C., et al.
Published: (2025)

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
by: Li, Xuan, et al.
Published: (2026)

Adaptive Diffusion Policy Optimization for Robotic Manipulation
by: Jiang, Huiyun, et al.
Published: (2025)

V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization
by: Jiang, Yubo, et al.
Published: (2026)

NGRPO: Negative-enhanced Group Relative Policy Optimization
by: Nan, Gongrui, et al.
Published: (2025)

From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization
by: Chen, Xinjie, et al.
Published: (2025)

Policy Guided Tree Search for Enhanced LLM Reasoning
by: Li, Yang
Published: (2025)

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
by: Xu, Zhangchen, et al.
Published: (2025)

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning
by: Feng, Wenfeng, et al.
Published: (2025)

Divergence-Augmented Policy Optimization
by: Wang, Qing, et al.
Published: (2025)

DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
by: Li, Gang, et al.
Published: (2025)

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
by: Di, Zixiang, et al.
Published: (2026)

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
by: Qu, Yun, et al.
Published: (2026)

GIPO: Gaussian Importance Sampling Policy Optimization
by: Lu, Chengxuan, et al.
Published: (2026)

DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs
by: Shu, Yubo, et al.
Published: (2025)

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
by: Yuan, Rui, et al.
Published: (2026)

Graph Unlearning Meets Influence-aware Negative Preference Optimization
by: Chen, Qiang, et al.
Published: (2025)

Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
by: Niu, Haoyi, et al.
Published: (2023)

Provable and Practical In-Context Policy Optimization for Self-Improvement
by: Yu, Tianrun, et al.
Published: (2026)

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies
by: Li, Xiang, et al.
Published: (2026)

Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
by: Jiang, Zuoyou, et al.
Published: (2025)

SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning
by: Jia, Furong, et al.
Published: (2026)

SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
by: Lin, Jiaye, et al.
Published: (2025)

Boosting LLM Reasoning via Human-Inspired Reward Shaping
by: Lin, Wenze, et al.
Published: (2026)

IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpus
by: Gui, Honghao, et al.
Published: (2024)

PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment
by: Li, Jiawei, et al.
Published: (2024)

A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models
by: Wang, Wenkai, et al.
Published: (2025)

EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
by: Jiao, Siwen, et al.
Published: (2025)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
by: Qu, Yuxiao, et al.
Published: (2026)

Preference as Reward, Maximum Preference Optimization with Importance Sampling
by: Jiang, Zaifan, et al.
Published: (2023)

Bridging Policy and Real-World Dynamics: LLM-Augmented Rebalancing for Shared Micromobility Systems
by: Tan, Heng, et al.
Published: (2026)

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
by: Wang, Ziyan, et al.
Published: (2025)