Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities

• URL: http://arxiv.org/abs/2508.20324v3
• Date: Sat, 11 Oct 2025 16:36:34 GMT
• Title: Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities
• Abstract summary: Reinforcement Learning has emerged as a dominant approach to elicit agentic RAG behaviors from language models.<n> compact models exhibit poor initial performance, resulting in sparse rewards and unstable training.<n>We propose Distillation-Guided Policy Optimization (DGPO) to overcome these difficulties.
• Score: 5.221077757149821
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning has emerged as a dominant post-training approach to elicit agentic RAG behaviors such as search and planning from language models. Despite its success with larger models, applying RL to compact models (e.g., 0.5--1B parameters) presents unique challenges. The compact models exhibit poor initial performance, resulting in sparse rewards and unstable training. To overcome these difficulties, we propose Distillation-Guided Policy Optimization (DGPO), which employs cold-start initialization from teacher demonstrations and continuous teacher guidance during policy optimization. To understand how compact models preserve agentic behavior, we introduce Agentic RAG Capabilities (ARC), a fine-grained metric analyzing reasoning, search coordination, and response synthesis. Comprehensive experiments demonstrate that DGPO enables compact models to achieve sophisticated agentic search behaviors, even outperforming the larger teacher model in some cases. DGPO makes agentic RAG feasible in computing resource-constrained environments.

Related papers

• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models [55.01951088768769]
  DiffusionOPD is a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD)<n>We show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-05-14T16:49:09Z)
• On Predicting the Post-training Potential of Pre-trained LLMs [60.07459271263409]
  We introduce a new task of predicting post-training potential - forecasting a base model's performance before post-training.<n>We propose RuDE, a unified framework that bypasses the generation gap of base models by leveraging response discrimination.<n>Experiments demonstrate a correlation greater than 90% with post-training performance.
  arXiv  Detail & Related papers  (2026-05-12T11:33:49Z)
• AIPO: Learning to Reason from Active Interaction [54.10819421625103]
  AIPO enables the policy model to proactively consult three functional collaborative agents when encountering reasoning bottlenecks.<n>AIPO consistently improves reasoning performance, generalizes robustly across different policy models and RLVR algorithms, and effectively expands the reasoning capability boundary of the policy model.
  arXiv  Detail & Related papers  (2026-05-08T19:06:55Z)
• Multimodal Reinforcement Learning with Agentic Verifier for AI Agents [131.46008226323423]
  Argos is a principled multimodal reward agent to train reasoning models for agentic tasks.<n>By leveraging our agentic verifier across both SFT data and RL training, our model achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2025-12-03T04:42:47Z)
• GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning [52.16150076582931]
  We propose Group Relative Policy Optimization for Representation Model (GRPO-RM)<n>Our method establishes a predefined output set to functionally replace token sequence sampling in large language models (LLMs)<n>A specialized reward function is designed to accommodate the properties of representation models.
  arXiv  Detail & Related papers  (2025-11-19T09:19:39Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges [6.615766570234612]
  Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models.<n>To address these challenges, the field has shifted toward Reasoning Agentic RAG, a paradigm that embeds decision-making and adaptive tool use directly into the retrieval process.
  arXiv  Detail & Related papers  (2025-06-12T07:01:56Z)
• GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models [0.17265013728931003]
  GRPO-LEAD is a suite of novel enhancements tailored for mathematical reasoning.<n>It introduces (1) a length-dependent accuracy reward to encourage concise and precise solutions, (2) an explicit penalty mechanism for incorrect answers to sharpen decision boundaries, and (3) a difficulty-aware advantage reweighting strategy that amplifies learning signals for challenging problems.
  arXiv  Detail & Related papers  (2025-04-13T19:07:45Z)
• Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models [0.0]
  We propose using prior model knowledge to guide the exploration process to speed up reinforcement learning.<n>We provide theoretical guarantees on the convergence of the Q-function to the optimal Q-function under the proposed class of exploring policies.
  arXiv  Detail & Related papers  (2025-04-08T12:33:38Z)
• Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning [75.9729413703531]
  DIPPER is a novel HRL framework that formulates hierarchical policy learning as a bi-level optimization problem.<n>We show that DIPPER achieves up to 40% improvement over state-of-the-art baselines in sparse reward scenarios.
  arXiv  Detail & Related papers  (2024-11-01T04:58:40Z)
• Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning [51.52387511006586]
  We propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies. HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios.
  arXiv  Detail & Related papers  (2024-06-12T08:48:06Z)
• Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration [15.463313629574111]
  This paper investigates how to achieve sample-efficient exploration in continuous control tasks. We introduce an RL algorithm that incorporates a predictive model and off-policy learning elements. We derive an intrinsic reward without incurring parameters overhead.
  arXiv  Detail & Related papers  (2024-03-31T11:39:11Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm [28.48626438603237]
  PACER consists of a distributional critic, an actor and a sample-based encourager. Push-forward operator is leveraged in both the critic and actor to model the return distributions and policies respectively. A sample-based utility value policy gradient is established for the push-forward policy update.
  arXiv  Detail & Related papers  (2023-06-11T09:45:31Z)
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment [32.752633250862694]
  Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. We introduce a new framework, Reward rAnked FineTuning, designed to align generative models effectively.
  arXiv  Detail & Related papers  (2023-04-13T18:22:40Z)
• Online reinforcement learning with sparse rewards through an active inference capsule [62.997667081978825]
  This paper introduces an active inference agent which minimizes the novel free energy of the expected future. Our model is capable of solving sparse-reward problems with a very high sample efficiency. We also introduce a novel method for approximating the prior model from the reward function, which simplifies the expression of complex objectives.
  arXiv  Detail & Related papers  (2021-06-04T10:03:36Z)
• Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts [52.844741540236285]
  This paper investigates the model-based methods in multi-agent reinforcement learning (MARL) We propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy (AORPO)
  arXiv  Detail & Related papers  (2021-05-07T16:20:22Z)
• On the model-based stochastic value gradient for continuous reinforcement learning [50.085645237597056]
  We show that simple model-based agents can outperform state-of-the-art model-free agents in terms of both sample-efficiency and final reward. Our findings suggest that model-based policy evaluation deserves closer attention.
  arXiv  Detail & Related papers  (2020-08-28T17:58:29Z)

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.