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

arXiv: https://arxiv.org/abs/2607.14777 · HTML: https://mlsanity.com/paper/2607.14777/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 52 of its 60 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)
- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 30 of 52)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)

## Built on by (most cited first, 30 of 32)

- [PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.01837/) (2026)
- [Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation](https://mlsanity.com/paper/2608.04788/) (2026)
- [Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization](https://mlsanity.com/paper/2608.31077/) (2026)
- [MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation](https://mlsanity.com/paper/2607.29320/) (2026)
- [Negative Self-Distillation: Learning to Reason by Avoiding Flaws](https://mlsanity.com/paper/2609.11699/) (2026)
- [Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents](https://mlsanity.com/paper/2609.08919/) (2026)
- [PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.36642/) (2026)
- [MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development](https://mlsanity.com/paper/2609.36679/) (2026)
- [RLTL;DR: Self-improvement by Internalizing Self-generated Feedback](https://mlsanity.com/paper/2609.37633/) (2026)
- [Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight](https://mlsanity.com/paper/2610.08077/) (2026)
- [Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings](https://mlsanity.com/paper/2609.15296/) (2026)
- [Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents](https://mlsanity.com/paper/2609.27869/) (2026)
- [HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection](https://mlsanity.com/paper/2609.32280/) (2026)
- [Trajectory Unlearning on LLM-based Agents](https://mlsanity.com/paper/2609.33639/) (2026)
- [SkillRubric: Co-Evolving Actor Guidance and Evaluator Rubrics for Multimodal Agents](https://mlsanity.com/paper/2609.34557/) (2026)
- [Revisit to Segment: Working Memory Distillation for Reasoning Segmentation](https://mlsanity.com/paper/2609.34863/) (2026)
- [TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL](https://mlsanity.com/paper/2609.35058/) (2026)
- [EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning](https://mlsanity.com/paper/2609.35290/) (2026)
- [PIVOT: Pivot-Aware On Policy Self Distillation for Multi-Turn VLM Agents](https://mlsanity.com/paper/2609.35303/) (2026)
- [Graph-Conditioned On-Policy Agent Distillation from Off-the-Shelf Teachers](https://mlsanity.com/paper/2609.37522/) (2026)
- [From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL](https://mlsanity.com/paper/2609.39436/) (2026)
- [ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents](https://mlsanity.com/paper/2609.40253/) (2026)
- [My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.01161/) (2026)
- [Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents](https://mlsanity.com/paper/2610.01787/) (2026)
- [ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience](https://mlsanity.com/paper/2610.05303/) (2026)
- [Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks](https://mlsanity.com/paper/2610.05383/) (2026)
- [Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation](https://mlsanity.com/paper/2610.07250/) (2026)
- [RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution](https://mlsanity.com/paper/2610.15772/) (2026)
- [Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning](https://mlsanity.com/paper/2610.17734/) (2026)
- [Agent-Reflex: Teaching Language Agents to Act Reflectively](https://mlsanity.com/paper/2610.17953/) (2026)

## Abstract (arXiv)

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.