arXiv AI
DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 31
Living-Harness Is an Interactive-Agent Evolver
arXiv:2607. 26598v1 Announce Type: cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions.
arXiv Machine Learning
Aug 4
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
arXiv:2608. 01918v1 Announce Type: new Abstract: Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments.
arXiv AI
Aug 28
Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification
The paper introduces HarnessLens, a budget‑aware framework that evolves language‑model agent harnesses by jointly exploring task spaces and user‑configurable components. It derives candidate modifications from execution trajectories and selectively verifies them on behavior‑relevant tasks using an attributable‑evidence gate, thereby avoiding wasteful rollouts on unrelated behaviors. Experiments on three harnesses and four benchmarks show that HarnessLens improves held‑out performance by 7.6‑13.6% while using less evaluation budget than existing methods.
arXiv Machine Learning
Jul 30
DREvo: Distilling Recalibrated Historical Experience for Harness Self-Evolution
arXiv:2607. 26722v1 Announce Type: cross Abstract: Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort.
arXiv AI
Jun 15
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
arXiv:2606. 14249v1 Announce Type: new Abstract: 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.
arXiv AI
2d ago
Learning from Research: Toward Lifelong Agent Harness Evolution
The paper introduces ScholarEvolve, a framework that evolves the software harness of language agents by automatically incorporating insights from recent research papers. It organizes harness improvements into functional modules, uses topic modeling to identify distinct strategies, and evaluates combinations to boost task performance. Experiments show significant gains on AppWorld and Tau2-Bench, raising Qwen3.5-27B completion rates from 49.6% to 63.6% and GPT-5.4-mini pass@1 from 72.7% to 81.9%.