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

• URL: http://arxiv.org/abs/2507.20278v1
• Date: Sun, 27 Jul 2025 13:52:15 GMT
• Title: MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent Reasoning
• Authors: Kang Yang, Jingxue Chen, Qingkun Tang, Tianxiang Zhang, Qianchun Lu,
• Abstract summary: MoL-RL is a novel training paradigm that integrates multi-step EF signals into large language models.<n>We show that MoL-RL achieves state-of-the-art performance with the Qwen3-8B model.
• Score: 3.486190892832845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) face significant challenges in effectively leveraging sequential environmental feedback (EF) signals, such as natural language evaluations, for feedback-independent chain-of-thought (CoT) reasoning. Existing approaches either convert EF into scalar rewards, losing rich contextual information, or employ refinement datasets, failing to exploit the multi-step and discrete nature of EF interactions. To address these limitations, we propose MoL-RL, a novel training paradigm that integrates multi-step EF signals into LLMs through a dual-objective optimization framework. Our method combines MoL (Mixture-of-Losses) continual training, which decouples domain-specific EF signals (optimized via cross-entropy loss) and general language capabilities (preserved via Kullback-Leibler divergence), with GRPO-based post-training to distill sequential EF interactions into single-step inferences. This synergy enables robust feedback-independent reasoning without relying on external feedback loops. Experimental results on mathematical reasoning (MATH-500, AIME24/AIME25) and code generation (CodeAgent-Test) benchmarks demonstrate that MoL-RL achieves state-of-the-art performance with the Qwen3-8B model, while maintaining strong generalization across model scales (Qwen3-4B). This work provides a promising approach for leveraging multi-step textual feedback to enhance LLMs' reasoning capabilities in diverse domains.

Related papers

• Advancing Multimodal Reasoning Capabilities of Multimodal Large Language Models via Visual Perception Reward [87.06604760273372]
  We propose Perception-R1, which introduces a novel visual perception reward that explicitly encourages MLLMs to perceive the visual content accurately.<n>We show that Perception-R1 achieves state-of-the-art performance on most benchmarks using only 1,442 training data.
  arXiv  Detail & Related papers  (2025-06-08T16:48:42Z)
• d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning [31.531278643184656]
  Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL)<n>We propose d1, a framework to adapt pre-trained masked dLLMs into reasoning models via a combination of supervised finetuning (SFT) and RL.<n>We find that d1 yields the best performance and significantly improves performance of a state-of-the-art dLLM.
  arXiv  Detail & Related papers  (2025-04-16T16:08:45Z)
• Distilling Transitional Pattern to Large Language Models for Multimodal Session-based Recommendation [67.84581846180458]
  Session-based recommendation (SBR) predicts the next item based on anonymous sessions.<n>Recent Multimodal SBR methods utilize simplistic pre-trained models for modality learning but have limitations in semantic richness.<n>We propose a multimodal LLM-enhanced framework TPAD, which extends a distillation paradigm to decouple and align transitional patterns for promoting MSBR.
  arXiv  Detail & Related papers  (2025-04-13T07:49:08Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models [83.77114091471822]
  Split federated learning (SFL) is a compute-efficient paradigm in distributed machine learning (ML) A challenge in SFL, particularly when deployed over wireless channels, is the susceptibility of transmitted model parameters to adversarial jamming. This is particularly pronounced for word embedding parameters in large language models (LLMs), which are crucial for language understanding. A physical layer framework is developed for resilient SFL with LLMs (R-SFLLM) over wireless networks.
  arXiv  Detail & Related papers  (2024-07-16T12:21:29Z)
• RLSF: Fine-tuning LLMs via Symbolic Feedback [11.407319705797242]
  Large Language Models (LLMs) have transformed AI but often struggle with tasks that require domain-specific reasoning and logical alignment.<n>Traditional fine-tuning methods do not leverage the vast amount of symbolic domain-knowledge available to us.<n>We introduce Reinforcement Learning via Symbolic Feedback (RLSF), a novel fine-tuning paradigm.
  arXiv  Detail & Related papers  (2024-05-26T18:49:59Z)
• IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues [10.280113107290067]
  The IM-RAG approach integrates Information Retrieval systems with Large Language Models (LLMs) to support multi-round RAG. The entire IM process is optimized via Reinforcement Learning (RL) where a Progress Tracker is incorporated to provide mid-step rewards. The results show that our approach achieves state-of-the-art (SOTA) performance while providing high flexibility in integrating IR modules.
  arXiv  Detail & Related papers  (2024-05-15T12:41:20Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction [13.245873138716044]
  Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Inspired by recent work, we explore leveraging large language model (LLM) to address ECPE task without additional training. We introduce chain-of-thought to mimic human cognitive process and propose the Decomposed Emotion-Cause Chain (DECC) framework.
  arXiv  Detail & Related papers  (2024-01-31T10:20:01Z)
• CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model [22.870512676002463]
  This paper focuses on Offsite-Tuning (OFT), a representative technique that transfers transformer blocks between centralized LLMs and downstream emulators. Inspired by these observations, we propose CRaSh, involving Clustering, Removing, and Sharing, a training-free strategy to derive improved emulators from LLMs. Our findings demonstrate a linear connectivity among these optima falling over the same basin, thereby highlighting the effectiveness of CRaSh and OFT.
  arXiv  Detail & Related papers  (2023-10-24T03:08:58Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.