Image de couverture de livre

MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Kang, Chen, Jingxue, Tang, Qingkun, Zhang, Tianxiang, Lu, Qianchun
Format:	Preprint
Publié:	2025
Sujets:	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

MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities
par: Chen, Jingxue, et autres
Publié: (2025)

Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval
par: Lin, Hao, et autres
Publié: (2025)

Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback
par: Xu, Hongshen, et autres
Publié: (2024)

LLMs are Superior Feedback Providers: Bootstrapping Reasoning for Lie Detection with Self-Generated Feedback
par: Banerjee, Tanushree, et autres
Publié: (2024)

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
par: Shi, Taiwei, et autres
Publié: (2024)

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback
par: Jiang, Dongwei, et autres
Publié: (2025)

Preference Optimization for Reasoning with Pseudo Feedback
par: Jiao, Fangkai, et autres
Publié: (2024)

Distilling Feedback into Memory-as-a-Tool
par: Gallego, Víctor
Publié: (2026)

Effective Distillation of Table-based Reasoning Ability from LLMs
par: Yang, Bohao, et autres
Publié: (2023)

PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling
par: Chen, Yongchao, et autres
Publié: (2024)

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
par: Chen, Angelica, et autres
Publié: (2023)

Multi-dimensional Assessment and Explainable Feedback for Counselor Responses to Client Resistance in Text-based Counseling with LLMs
par: Li, Anqi, et autres
Publié: (2026)

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
par: Zhang, Xiaoying, et autres
Publié: (2025)

Learning GUI Grounding with Spatial Reasoning from Visual Feedback
par: Zhao, Yu, et autres
Publié: (2025)

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
par: Lu, Zimu, et autres
Publié: (2025)

REFINER: Reasoning Feedback on Intermediate Representations
par: Paul, Debjit, et autres
Publié: (2023)

Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation
par: Zhu, Xunyu, et autres
Publié: (2024)

QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction
par: Huang, Xiang, et autres
Publié: (2024)

Learning to Reason via Self-Iterative Process Feedback for Small Language Models
par: Chen, Kaiyuan, et autres
Publié: (2024)

FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback
par: Li, Youquan, et autres
Publié: (2024)

Mission Impossible: Feedback-Guided Dynamic Interactive Planning for Improving Reasoning on LLMs
par: Yan, Dong, et autres
Publié: (2025)

Training Language Models to Critique With Multi-agent Feedback
par: Lan, Tian, et autres
Publié: (2024)

KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation
par: Fang, Siyuan, et autres
Publié: (2024)

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
par: Mishra, Venkatesh, 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)

Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use
par: Goldie, Anna, et autres
Publié: (2025)

Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback
par: Moon, Seungjun, et autres
Publié: (2023)

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
par: Wang, Xingyao, et autres
Publié: (2023)

Matrix as Plan: Structured Logical Reasoning with Feedback-Driven Replanning
par: Chen, Ke, et autres
Publié: (2026)

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback
par: Yun, Taewon, et autres
Publié: (2025)

SAFE: Stepwise Atomic Feedback for Error correction in Multi-hop Reasoning
par: Kwon, Daeyong, et autres
Publié: (2026)

Multi-turn Training with Basic Human Feedback Helps Little on LLM Reasoning
par: Liu, Qiang, et autres
Publié: (2025)

CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning
par: Rufail, Andrew, et autres
Publié: (2025)

Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization
par: Seo, Wonduk, et autres
Publié: (2025)

Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
par: Li, Zhuowan, et autres
Publié: (2024)

LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback
par: Lai, Wen, et autres
Publié: (2024)

FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
par: Fan, Zhiting, et autres
Publié: (2024)

LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs
par: Lian, Da-Chen, et autres
Publié: (2025)

Time-Reversal Provides Unsupervised Feedback to LLMs
par: Varun, Yerram, et autres
Publié: (2024)

Small But Funny: A Feedback-Driven Approach to Humor Distillation
par: Ravi, Sahithya, et autres
Publié: (2024)