Image de couverture de livre

Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Yixiao, Li, Yang, Cheng, Dongzhou, Fan, Hehe, Cheng, Yu
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
par: Zhou, Yixiao, et autres
Publié: (2026)

Looking Inward: Language Models Can Learn About Themselves by Introspection
par: Binder, Felix J, et autres
Publié: (2024)

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment
par: Zhang, Jinghao, et autres
Publié: (2025)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
par: Limozin, Alexis, et autres
Publié: (2026)

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
par: Zhou, Yifei, et autres
Publié: (2024)

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
par: Liu, Bingshuai, et autres
Publié: (2025)

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
par: Yang, Ling, et autres
Publié: (2025)

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
par: Shen, Guobin, et autres
Publié: (2026)

FlowRL: Matching Reward Distributions for LLM Reasoning
par: Zhu, Xuekai, et autres
Publié: (2025)

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
par: Liu, Shih-Yang, et autres
Publié: (2026)

Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards
par: Padula, Alexander G., et autres
Publié: (2024)

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control
par: Yao, Xincheng, et autres
Publié: (2026)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
par: Li, Haozhan, et autres
Publié: (2025)

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
par: Qian, Cheng, et autres
Publié: (2025)

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
par: Luo, Sijia, et autres
Publié: (2026)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
par: Wei, Zhepei, et autres
Publié: (2025)

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
par: Feng, Xiao, et autres
Publié: (2026)

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
par: Zhou, Zhi, et autres
Publié: (2025)

Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
par: Shi, Zhenning, et autres
Publié: (2026)

ToolRL: Reward is All Tool Learning Needs
par: Qian, Cheng, et autres
Publié: (2025)

OUTLINEFORGE: Hierarchical Reinforcement Learning with Explicit States for Scientific Writing
par: Bao, Yilin, et autres
Publié: (2026)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
par: Zhang, Shenao, et autres
Publié: (2025)

Enhancing Large Language Models through Structured Reasoning
par: Dong, Yubo, et autres
Publié: (2025)

Learning to Reason under Off-Policy Guidance
par: Yan, Jianhao, et autres
Publié: (2025)

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
par: Yu, Hongli, et autres
Publié: (2025)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
par: Zhou, Jin Peng, et autres
Publié: (2025)

Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning
par: Liu, Qihao, et autres
Publié: (2025)

Co-Evolution of Policy and Internal Reward for Language Agents
par: Wang, Xinyu, et autres
Publié: (2026)

ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
par: Lu, Xingyu, et autres
Publié: (2026)

Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling
par: Fan, Hehe, et autres
Publié: (2025)

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
par: Wang, Ziyan, et autres
Publié: (2025)

CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
par: Cui, Sijia, et autres
Publié: (2026)

Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
par: Zhao, Anhao, et autres
Publié: (2026)

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
par: Bin, Yi, et autres
Publié: (2025)

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
par: Hu, Xing, et autres
Publié: (2024)

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning
par: Huang, Wei, et autres
Publié: (2026)

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning
par: Chen, Zizhe, et autres
Publié: (2026)

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
par: Xu, Ran, et autres
Publié: (2025)

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
par: Yang, Zhuolin, et autres
Publié: (2026)

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
par: Yang, Zonglin, et autres
Publié: (2025)