# A Theory of Reliable Self-Evolution for Agent Harnesses

arXiv: https://arxiv.org/abs/2609.08175 · HTML: https://mlsanity.com/paper/2609.08175/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [A Self-Improving Coding Agent](https://mlsanity.com/paper/2504.15228/) (2025)
- [Hyperagents](https://mlsanity.com/paper/2603.19461/) (2026)
- [Huxley-G"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine](https://mlsanity.com/paper/2510.21614/) (2025)
- [HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry](https://mlsanity.com/paper/2606.14249/) (2026)
- [G"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement](https://mlsanity.com/paper/2410.04444/) (2024)
- [TTHE: Test-Time Harness Evolution](https://mlsanity.com/paper/2607.08124/) (2026)
- [MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems](https://mlsanity.com/paper/2605.22794/) (2026)
- [PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents](https://mlsanity.com/paper/2606.08106/) (2026)
- [SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification](https://mlsanity.com/paper/2510.10232/) (2025)
- [On The Statistical Limits of Self-Improving Agents](https://mlsanity.com/paper/2510.04399/) (2025)

## Built on by (most cited first, 2 of 2)

- [Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts](https://mlsanity.com/paper/2609.18366/) (2026)
- [Self-Evolving Agent Harness](https://mlsanity.com/paper/2610.18813/) (2026)

## Abstract (arXiv)

In harness self-evolution, agents modify their own prompts, code, tools, and orchestration while keeping the underlying language model fixed. Recent work has shown that agents can improve themselves in response to task failures and achieve substantial performance gains. However, gains on failed tasks do not automatically ensure that performance on previously successful tasks is preserved, raising concerns about reliable adoption. In this work, we provide a theoretically grounded condition under which a self-evolved harness can be reliably adopted. We then propose a validation rule to make the evolved system satisfy the reliable adoption condition with theoretical guarantees. Consequently, the system can achieve progressive improvement through evolution. This leads to a natural question: Does reliable self-evolution have a performance ceiling, and which factors govern this ceiling? Our theoretical results show that the performance ceiling is determined by the costs of verification and evaluation. On the other hand, self-evolution may stall in practice. In this regard, we show that experimental evidence on agent performance shifts can be used to identify the sources of stagnation. Our work thus establishes a theoretical framework for understanding and advancing reliable harness self-evolution.