# Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement

arXiv: https://arxiv.org/abs/2511.05931 · HTML: https://mlsanity.com/paper/2511.05931/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Builds on (most cited first, 30 of 35)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [LocAgent: Graph-Guided LLM Agents for Code Localization](https://mlsanity.com/paper/2503.09089/) (2025)
- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration](https://mlsanity.com/paper/2406.01422/) (2024)
- [Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents](https://mlsanity.com/paper/2408.07060/) (2024)
- [EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations](https://mlsanity.com/paper/2410.22821/) (2024)
- [CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models](https://mlsanity.com/paper/2411.04329/) (2024)
- [SweRank: Software Issue Localization with Code Ranking](https://mlsanity.com/paper/2505.07849/) (2025)

## Built on by (most cited first, 9 of 9)

- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution](https://mlsanity.com/paper/2603.01327/) (2026)
- [From Plan to Action: How Well Do Agents Follow the Plan?](https://mlsanity.com/paper/2604.12147/) (2026)
- [LLM Agents Can See Code Repositories](https://mlsanity.com/paper/2606.14061/) (2026)
- [Self-Evolving Coding Agents](https://mlsanity.com/paper/2608.03392/) (2026)
- [Online Monitoring and Corrective Steering of Programming Agents](https://mlsanity.com/paper/2608.06701/) (2026)
- [SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution](https://mlsanity.com/paper/2608.18933/) (2026)
- [Reusing Past Repairs Through Hierarchical Trajectory Abstraction for Coding Agents](https://mlsanity.com/paper/2607.29658/) (2026)

## Abstract (arXiv)

Large language model (LLM) based agents are increasingly used to tackle software engineering tasks that require multi-step reasoning and code modification, demonstrating promising yet limited performance. However, most existing LLM agents typically operate within static execution frameworks, lacking a principled mechanism to learn and self-improve from their own experience and past rollouts. As a result, their performance remains bounded by the initial framework design and the underlying LLM's capabilities. We propose Self-Abstraction from Grounded Experience (SAGE), a framework that enables agents to learn from their own task executions and refine their behavior through self-abstraction. After an initial rollout, the agent induces a concise plan abstraction from its grounded experience, distilling key steps, dependencies, and constraints. This learned abstraction is then fed back as contextual guidance, refining the agent's policy and supporting more structured, informed subsequent executions. Empirically, SAGE delivers consistent performance gains across diverse LLM backbones and agent architectures. Notably, it yields a 7.2% relative performance improvement over the strong Mini-SWE-Agent baseline when paired with the GPT-5 (high) backbone. SAGE further achieves strong overall performance on SWE-Bench Verified benchmark, reaching 73.2% and 74% Pass@1 resolve rates with the Mini-SWE-Agent and OpenHands CodeAct agent framework, respectively.