HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Summary
HarnessX is a foundry for composable, adaptive, and evolvable AI agent harnesses that uses compositional primitives and trace-driven evolution to improve agent performance. Across five benchmarks, it achieves an average gain of +14.5% (up to +44.0%), demonstrating that runtime interface evolution is a complementary lever to model scaling.
View Cached Full Text
Cached at: 06/15/26, 09:04 AM
Paper page - HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Source: https://huggingface.co/papers/2606.14249 Authors:
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
HarnessX enables adaptive and evolvable AI agent runtime interfaces through compositional primitives, trace-driven evolution, and feedback loops that improve both harness design and model training.
AIagent performancedepends critically on theruntime harness, comprising theprompts,tools,memory, andcontrol flowthat mediate how a model observes, reasons, and acts. Yet today’s harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via asubstitution algebra, adapts them throughAEGIS, a trace-drivenmulti-agent evolution enginegrounded in anoperational mirrorbetweensymbolic adaptationandreinforcement learning, and closes theharness-model loopby turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces fromexecution feedbackis an actionable and complementary lever. The complete codebase will be open-sourced in a future release.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2606\.14249
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.14249 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.14249 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.14249 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
@NFTCPS: HarnessX is pretty interesting: an agent architecture that can modify itself. Previously, architectural changes relied entirely on manual tuning. When a new model came out, Anthropic removed the planning steps from Claude Code, and Manus refactored its agents five times in six months, each time simplifying. What to change and when to change it — all decided by humans.
HarnessX introduces a framework for self-evolving AI agent harnesses that treats the runtime harness as a first-class object, enabling automatic adaptation via trace-driven reinforcement learning. It achieves average gains of +14.5% across five benchmarks, with larger improvements for weaker models.
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
HarnessForge proposes a meta-adaptive framework for evolving LLM agent systems by jointly optimizing the execution harness and reasoning policy, achieving consistent improvements on Qwen3 backbones across five benchmarks.
@AlphaSignalAI: https://x.com/AlphaSignalAI/status/2074130508833845396
Self-improving harnesses enable AI agents to autonomously rewrite their operating rules by analyzing execution traces, leading to a 60% performance boost. Research from Shanghai AI Lab introduces the Self-Harness framework, allowing lightweight models to outperform larger ones without manual engineering.
Harness design for long-running application development
Anthropic engineers detail a multi-agent harness design using generator and evaluator agents to improve Claude's ability to build complete, high-quality frontend applications autonomously over long durations.
@omarsar0: // Self-Harness: Harnesses That Improve Themselves // (bookmark this one) Most of the agent scaffolds we rely on today …
This paper introduces Self-Harness, a new paradigm where LLM-based agents iteratively improve their own operating harness—prompts, tools, and control flow—without human engineers or stronger external agents, achieving significant performance gains across multiple models.