SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

• URL: http://arxiv.org/abs/2607.14777v1
• Date: Thu, 16 Jul 2026 09:57:18 GMT
• Title: SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
• Abstract summary: Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions.<n>We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills.
• Score: 38.54413500261524
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model. SEED first fine-tunes the policy to analyze completed trajectories and generate natural-language skills that capture reusable workflows, decisive observations, or failure-avoidance rules. During RL, the current policy both collects trajectories and serves as the analyzer that extracts hindsight skills from them. Policy updates therefore improve subsequent decision making and skill analysis together, allowing hindsight supervision to evolve with the policy. SEED then re-scores the sampled actions under ordinary and skill-augmented contexts, converting the skill-induced probability shift into a dense token-level on-policy distillation signal. This signal is jointly optimized with outcome-based RL, keeping the auxiliary supervision aligned with the current trajectory distribution. Extensive experiments on text-based and vision-based agentic tasks show that SEED consistently improves performance and sample efficiency, exhibiting robust generalization to unseen scenarios. Our code is available at https://github.com/jinyangwu/SEED.

Related papers

• Self-Improving Large Language Models via Progressive Experience Evolution [52.03479747358687]
  We propose textbfSPEE (textbfSelf-textbfProgressive textbfExperience textbfEvolution), a unified post-training framework that sequentially performs explicit experience evolution followed by implicit policy optimization.<n> Experiments on five mathematical reasoning benchmarks demonstrate that SPEE consistently outperforms both test-time and training-time self-evolution baselines across three model scales.
  arXiv  Detail & Related papers  (2026-08-03T12:27:32Z)
• Group-Reflective Self-Distillation for Agentic Reinforcement Learning [8.041052886037766]
  Group-Reflective Self-Distillation (GRSD) derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts.<n>GRSD consistently outperforms competitive baselines and generalizes more effectively to unseen tasks.
  arXiv  Detail & Related papers  (2026-07-30T11:49:46Z)
• SPyCE: Skill-Policy Co-evolution for Multimodal Agents [12.105041985483167]
  We propose SPyCE, a framework that distills trajectories into a hierarchical skill library and updates it throughout reinforcement learning.<n>During training, the policy model conditions on retrieved skills to guide its rollouts, while the skill library evolves using valuable rollouts generated by the policy.<n> Experiments across eight benchmarks demonstrate that SPyCE consistently outperforms both RL-based and memory-based baselines.
  arXiv  Detail & Related papers  (2026-07-15T14:01:48Z)
• OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning [38.54413500261524]
  On-policy self-distillation offers dense token-level supervision.<n>textbfOPID (textbfOn-textbfPolicy Sktextbfill textbfDistillation) is a framework that extracts skill supervision directly from completed on trajectories.
  arXiv  Detail & Related papers  (2026-06-25T09:24:09Z)
• From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving [56.30087557121323]
  AlignADV is a learnability-guided closed-loop adversarial training framework.<n>It converts adversarial scenarios into resolvable and capability-aligned curricula.<n> Experiments show it reduces training steps by up to 40.6 percent.
  arXiv  Detail & Related papers  (2026-06-12T02:13:55Z)
• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• COVLM-RL: Critical Object-Oriented Reasoning for Autonomous Driving Using VLM-Guided Reinforcement Learning [55.83415345423854]
  We propose COVLM-RL, a novel end-to-end driving framework that integrates Critical Object-oriented (CO) reasoning with reinforcement learning (RL)<n>Experiments conducted in the CARLA simulator demonstrate that COVLM-RL significantly improves the success rate by 30% in trained driving environments.
  arXiv  Detail & Related papers  (2025-12-10T06:18:16Z)
• Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning [41.90621652673528]
  We propose SPEAR, a curriculum-based self-imitation learning (SIL) recipe for training agentic LLMs.<n>Specifically, our approach incorporates a curriculum to manage the exploration process, utilizing intrinsic rewards to foster skill-level exploration.<n>To further stabilize training, we recalibrate the advantages of experiences in the replay buffer to address the potential policy drift.
  arXiv  Detail & Related papers  (2025-09-26T17:20:38Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)

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.