Cover Image

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Zhenwen, Lu, Sidi, Yu, Wenhao, Panaganti, Kishan, Zhou, Yujun, Mi, Haitao, Yu, Dong
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning
by: Panaganti, Kishan, et al.
Published: (2026)

Guided Self-Evolving LLMs with Minimal Human Supervision
by: Yu, Wenhao, et al.
Published: (2025)

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
by: Shi, Yucheng, et al.
Published: (2026)

Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
by: Liu, Rui, et al.
Published: (2025)

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
by: Liang, Zhenwen, et al.
Published: (2026)

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
by: Yu, Dian, et al.
Published: (2025)

MARGE: Improving Math Reasoning for LLMs with Guided Exploration
by: Gao, Jingyue, et al.
Published: (2025)

Stable and Efficient Single-Rollout RL for Multimodal Reasoning
by: Liu, Rui, et al.
Published: (2025)

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
by: Dai, Runpeng, et al.
Published: (2025)

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
by: Zhang, Ziyin, et al.
Published: (2025)

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
by: Zhou, Yujun, et al.
Published: (2025)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
by: Deng, Wenhao, et al.
Published: (2025)

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving
by: Liang, Zhenwen, et al.
Published: (2025)

Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization
by: Qu, Chengrui, et al.
Published: (2026)

MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
by: Liang, Zhenwen, et al.
Published: (2024)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
by: Yue, Murong, et al.
Published: (2024)

In-context Exploration-Exploitation for Reinforcement Learning
by: Dai, Zhenwen, et al.
Published: (2024)

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
by: Liang, Zhenwen, et al.
Published: (2025)

Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
by: Liu, Haolin, et al.
Published: (2026)

Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps
by: Cui, Yu, et al.
Published: (2025)

Guiding Exploration in Reinforcement Learning Through LLM-Augmented Observations
by: Jain, Vaibhav, et al.
Published: (2025)

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
by: Yao, Wenlin, et al.
Published: (2024)

The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
by: Liu, Xiaoyuan, et al.
Published: (2026)

R-Zero: Self-Evolving Reasoning LLM from Zero Data
by: Huang, Chengsong, et al.
Published: (2025)

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
by: Xu, Zaiyan, et al.
Published: (2025)

Reinforcement Learning by Guided Safe Exploration
by: Yang, Qisong, et al.
Published: (2023)

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
by: Li, Mukai, et al.
Published: (2025)

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees
by: Ganguly, Sourav, et al.
Published: (2025)

KL-regularization Itself is Differentially Private in Bandits and RLHF
by: Zhang, Yizhou, et al.
Published: (2025)

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
by: Zhou, Yang, et al.
Published: (2025)

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
by: Wang, Wenkai, et al.
Published: (2026)

LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation
by: Tan, Heng, et al.
Published: (2025)

Mission Impossible: Feedback-Guided Dynamic Interactive Planning for Improving Reasoning on LLMs
by: Yan, Dong, et al.
Published: (2025)

DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
by: Liang, Tian, et al.
Published: (2025)

From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
by: Han, Wei, et al.
Published: (2025)

Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
by: Liang, Zhenwen, et al.
Published: (2024)

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
by: Ma, Xinyu, et al.
Published: (2026)

Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
by: Wan, Yuxuan, et al.
Published: (2026)

LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
by: Zhou, Qianrui, et al.
Published: (2025)

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
by: He, Zhiwei, et al.
Published: (2025)