Search papers, labs, and topics across Lattice.
This paper introduces HarnessX, a novel framework for creating adaptive and evolvable agent harnesses that enhance AI agent performance by utilizing a substitution algebra for composable harness primitives and a trace-driven evolution engine called AEGIS. By integrating feedback from agent execution into both harness updates and model training, HarnessX achieved an average performance improvement of 14.5% across five benchmarks, with some tasks seeing gains of up to 44%. These findings indicate that optimizing runtime interfaces can significantly boost agent capabilities without solely relying on model scaling.
HarnessX reveals that evolving agent harnesses through execution feedback can outperform traditional model scaling, achieving up to 44% performance gains in specific tasks.
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that 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 a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by 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 from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.
