Skip to content
Preprint

A Theory of Reliable Self-Evolution for Agent Harnesses

Sep 2026 · 3 citations · ⚡ 2 influential
Computer Science

TL;DR

This work provides a theoretically grounded condition under which a self-evolved harness can be reliably adopted and proposes a validation rule to make the evolved system satisfy the reliable adoption condition with theoretical guarantees.

Abstract

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.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap as the problem of agentic abstention, and existing approaches typically optimize...

Hang Luo, Bing-Bing Wen, Guang Yang et al. · 1 citation
#artificial intelligence Preprint Oct 2026

VERSE: Verified Self-Evolving Optimizer for Agent Harnesses

VersE, a Verified Self-Evolving optimizer for agent harnesses, improves all four evaluated harness optimizers on held-out SWE-rebench tasks and newer out-of-distribution tasks in five languages.

Ze-Kai Wang, Ying-Qiang Ge, Ze-Kun Wang et al. · 2 citations
#artificial intelligence Preprint Sep 2026

Self-Healing Harness for Runtime Oversight of Agent Self-Modification

Across 16 matched Baseline and Harness runs spanning AppWorld, Terminal-Bench, and $\tau^2$-Bench, the gate rejected 383 replay-decided proposals, showing that locally beneficial self-modifications can introduce collateral regressions often enough to materially affect gate decisions, providing direct empirical motivati...

Sina Tayebati, Divake Kumar, Nastaran Darabi et al. · 0 citations
#artificial intelligence Preprint Oct 2026

AgentEvolver: System-Wide Self-Evolution Through Task Execution

This work presents AgentEvolver, a system for developing capabilities during task execution while keeping the foundation model fixed, and evaluates task outcomes on SWE-bench Pro Public and examines capability changes in six application cases.

Wen-Tao Zhang, Fu-Chao Yang, Yi-Lei Zhao et al. · 0 citations
#natural language process... Preprint Sep 2026

EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?

EvoHarnessBench is introduced, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents), and establishes harness evolution as a distinct challenge for building agents that can keep pace with an evolving harness while preserving previously effective behavior.

Zi-Xuan Ke, Vaidehi Patil, Hai-Zhou Shi et al. · 5 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.