HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution

arXiv:2607.13683v2 Announce Type: replace Abstract: Large Language Models (LLMs) have enabled capable agents across diverse applications. Beyond the foundation model, the performance of an agent is governed by the surrounding agent harness, including prompts, tools, control loops, etc. Automatically evolving this harness offers a promising pathway to agent improvement, yet existing approaches typically rely on greedy candidate selection and noisy self-generated feedback, rendering their gains susceptible to search collapse, task-specific overfitting, and poor verifiability. To tackle these challenges, we introduce HarnessBank, a trustworthy agent-harness self-evolution framework that pairs a task agent with a separate evolver agent for iterative failure diagnosis, harness generation, and evolution verification. HarnessBank maintains a Harness Gene Bank composed of high-performing harnesses of different semantic coordinates. Those harnesses are reinvented, recombined, screened, and selected during the self-evolution procedure. Moreover, we propose a Gated Harness Screening mechanism to efficiently filter high-quality harnesses and reduce the cost of evaluating numerous offspring harnesses. Across seven agent benchmarks, HarnessBank produces consistent performance improvements from 5.1% to 15.4%. Cross-model experiments further verify that the improvements come from the model-specific self-evolving process, instead of a universally optimal harness. Our code will be publicly available upon acceptance.

Related

• SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
• MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA
• SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams

Source: arXiv cs.CL | 2026-08-03