# DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution

arXiv: https://arxiv.org/abs/2607.26722 · HTML: https://mlsanity.com/paper/2607.26722/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 11 of 11)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making](https://mlsanity.com/paper/2410.07166/) (2024)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [OpenClaw-RL: Train Any Agent Simply by Talking](https://mlsanity.com/paper/2603.10165/) (2026)
- [Meta Context Engineering via Agentic Skill Evolution](https://mlsanity.com/paper/2601.21557/) (2026)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue](https://mlsanity.com/paper/2601.05589/) (2026)

## Built on by (most cited first, 5 of 5)

- [AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces](https://mlsanity.com/paper/2608.23041/) (2026)
- [Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection](https://mlsanity.com/paper/2608.20169/) (2026)
- [Mixture of Self-Improving Branches For Agent Harness Optimization](https://mlsanity.com/paper/2609.37834/) (2026)
- [ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization](https://mlsanity.com/paper/2610.00906/) (2026)
- [Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents](https://mlsanity.com/paper/2610.13991/) (2026)

## Abstract (arXiv)

Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort. Therefore, recent research has increasingly explored harness self-evolution, which iteratively proposes, evaluates, and improves harnesses using historical trial experience. However, accumulated historical experience does not always translate into stable search guidance, and performance often fluctuates substantially across evolution iterations, making it difficult to reliably discover high-performing harnesses under a limited evolution budget. We identify two limitations in how existing harness self-evolution methods leverage historical experience: (1) Lack of dynamic reassessment of whether historical experience remains valid for the current harness, and (2) Lack of explicit mechanisms for translating valid historical experience into actionable search directions. To address these limitations, we propose a new harness self-evolution method, named DREvo, which integrates function-level evidence anchoring, state-dependent evidence recalibration, and role-conditioned search intent distillation to determine which historical evidence remains valid and where the harness should evolve next. Under limited evolution budgets, DREvo exhibits smoother evolution trajectories, achieves the highest accuracy on all five benchmarks, and delivers average gains of 16.2% and 14.2% over the evaluated baselines on domain reasoning and agentic tasks, respectively.