Skip to content

LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks

Sep 2026 · 1 citation · ⚡ 1 influential · 57 references
Computer Science

TL;DR

LiteEvo is proposed, a lightweight harness-evolution algorithm whose tool-free meta-agents mine agent trajectories for reusable components, curate them into a versioned library, and compose each round's harness from it, starting every benchmark from the same neutral harness and never naming the benchmark.

Abstract

An LLM agent is defined by two things: the weights inside its model and the harness of components assembled around it. Harnesses are still handcrafted, and HarnessX, which evolves them automatically, starts each benchmark from a handcrafted harness, reports gains on the tasks it evolved on, and budgets 100 to 175 million meta-agent tokens per benchmark. We propose LiteEvo, a lightweight harness-evolution algorithm whose tool-free meta-agents mine agent trajectories for reusable components, curate them into a versioned library, and compose each round's harness from it, starting every benchmark from the same neutral harness and never naming the benchmark. Evolving on the graded tasks of five agentic benchmarks with a frozen Qwen3.5-9B, LiteEvo lifts pass@2 by 10.5 to 67.7pp and reaches comparable or higher pass@2 than a reproduction of HarnessX (71.0 against 67.3 on average) at 13.0 lower mean API cost. Harnesses evolved on train tasks keep their gains on unseen test tasks of four benchmarks, and LiteEvo also lifts Claude Code with Sonnet 4.6 by 1.2 to 71.4pp.

View source

Similar papers

#machine learning Preprint Aug 2026

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

To the authors' knowledge, JIT-Agent is the first model purpose-built for just-in-time harness generation, establishing harness intelligence as a trainable, transferable, and compounding dimension of agent capability orthogonal to model scaling.

Gui-Bin Zhang, Leo Lu, Fang-Zhou Xie et al. · 14 citations
#artificial intelligence Preprint Oct 2026

Harness Evolution Hits a Ceiling: When Weight Training Should Begin

Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the system stronger first, then cross seed and evolved harnesses with base and trained weights to learn which gains the trained model keeps and which still need the runtime. W...

Yuan Tian, Bing Hu, Hao Wang et al. · 0 citations
#artificial intelligence Preprint Aug 2026

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model with online rejection-sampling fine-tuning and Meta-Harness, is proposed.

Haechan Kim, Yoonho Lee, Gisang Lee et al. · 11 citations · ⚡4

Related blog posts

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