Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness.
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:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve executio...
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
Ecdysis is a framework for training runtime harnesses for large language model agents more efficiently. It distinguishes between model‑specific issues and systematic harness deficiencies by aggregating failures across multiple task instances and uses Failure‑Driven Collaborative Refinement to diagnose and fix harness problems. The approach reduces training time by up to 1.84× and improves harness reasoning accuracy by 18.56%.
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: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:2608. 15071v1 Announce Type: new Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.
Ecdysis is a framework for training runtime harnesses for large language model agents that reduces training time and improves performance. It distinguishes between model‑specific issues and systematic harness deficiencies by aggregating failures across multiple task instances and uses Failure‑Driven Collaborative Refinement to diagnose and correct harness problems. Experiments show up to a 1.84× speedup in harness training and an 18.56% increase in reasoning accuracy.
arXiv:2606. 07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions.
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%.
Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
arXiv:2602. 10226v2 Announce Type: replace-cross Abstract: Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures, and reward functions to capture nuanced user behaviors.