Self-Harness: Harnesses That Improve Themselves

• URL: http://arxiv.org/abs/2606.09498v1
• Date: Mon, 08 Jun 2026 13:50:23 GMT
• Title: Self-Harness: Harnesses That Improve Themselves
• Abstract summary: Self-Harness is a new paradigm in which an LLM-based agent improves its own operating harness without relying on human engineers or stronger external agents.<n>We instantiate Self-Harness on Terminal-Bench-2.0 using a minimal initial harness and three base models from diverse families.
• Score: 30.839060071524433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit distinct behaviors, effective harness design is inherently model-specific. Yet agent harnesses are still largely engineered by human experts, a paradigm that scales poorly as modern LLMs become increasingly diverse and rapidly evolving. In this paper, we introduce Self-Harness, a new paradigm in which an LLM-based agent improves its own operating harness, without relying on human engineers or stronger external agents. We operationalize Self-Harness as an iterative loop with three stages: Weakness Mining, which identifies model-specific failure patterns from execution traces; Harness Proposal, which generates diverse yet minimal harness modifications tied to these failures; and Proposal Validation, which accepts candidate edits only after regression testing. We instantiate Self-Harness on Terminal-Bench-2.0 using a minimal initial harness and three base models from diverse families: MiniMax M2.5, Qwen3.5-35B-A3B, and GLM-5. Across all three models, Self-Harness consistently improves performance, with held-out pass rates increasing from 40.5% to 61.9%, 23.8% to 38.1%, and 42.9% to 57.1%, respectively. Qualitative analyses further show that Self-Harness does not simply add generic instructions, but effectively turns model-specific weaknesses into concrete, executable harness changes. These results suggest a path toward LLM-based agents that are not merely shaped by their harnesses, but can also participate in reshaping them.

Related papers

• Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails [23.287109132562403]
  Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost.<n>We show that imitation transfers knowledge and increases scaffold usage, but disrupts model-harness fit.<n>We develop an on-policy expert-correction pipeline, automated by a meta-level MLE agent, that localizes the failing turn in the weaker model's own rollout and asks the expert to rewrite only that turn.
  arXiv  Detail & Related papers  (2026-09-08T17:53:49Z)
• HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? [61.02699867449589]
  We introduce HarnessDev, a benchmark that shifts the unit of evaluation from task outputs to run infrastructure.<n>In Creation, the agent starts from a minimal seed and a small number of cases, then builds a complete execution system.<n>In Evolution, it starts from its own created harness and iteratively revises it using downstream execution feedback, with the goal of improving benchmark performance.
  arXiv  Detail & Related papers  (2026-09-01T15:45:33Z)
• JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution [74.58840188662151]
  JIT-Agent is a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly.<n>JIT-Agent is the first model purpose-built for just-in-time harness generation.
  arXiv  Detail & Related papers  (2026-08-26T10:05:33Z)
• AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses [72.0777620499307]
  We study whether a stronger builder model can construct inference-time harnesses that help a weaker target model solve tasks more reliably without any parameter updates.<n> Empirically, this form of test-time capability transfer is highly effective, nearly doubling average target-model performance from 0.49 to 0.91.<n>We find that builder-model reasoning effort improves harness quality monotonically, platform effects are modest relative to the builder model's own capability, and weaker target models receive the largest gains.
  arXiv  Detail & Related papers  (2026-08-12T17:53:18Z)
• Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents [37.91666123749406]
  Co-Harness is a framework that jointly optimize the agent harness and model parameters during post-training.<n>An autonomous case study shows that Co-Harness can recover from system crashes, improve inference efficiency, and discover ensemble strategies without human intervention.
  arXiv  Detail & Related papers  (2026-07-17T02:39:57Z)
• Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents [80.03824805228719]
  A major challenge in developing computer-use agents is collecting large-scale, high-quality trajectories.<n>We propose a data-centric paradigm that turns failed trajectories into agent improvements.<n>We validate this approach with the state-of-the-art OpenCUA-72B model on the OSWorld benchmark.
  arXiv  Detail & Related papers  (2026-06-30T07:44:37Z)
• Dissecting model behavior through agent trajectories [15.811597127775812]
  We formalize the intent-execution' gap: the mismatch between what the model intends and what the harness executes, and vice versa.<n>To illustrate the impact of this harness-model alignment, we develop a simple and customizable harness called Simple Strands Agent' (SSA)<n>We make two contributions: (i) we reproduce or improve on the pass@1 performance reported by diverse model-provider families on popular agentic benchmarks, and (ii) building on an analysis of 138k trajectories generated by SSA.
  arXiv  Detail & Related papers  (2026-06-16T03:17:03Z)
• Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts [51.55077364626896]
  We introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimize agent harness using only past trajectories.<n>RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel.<n>A single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading.
  arXiv  Detail & Related papers  (2026-06-04T09:26:00Z)
• Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents [82.27610290890475]
  We analyze two harness self-evolution capabilities: (i) harness-updating, the capability to produce useful persistent harness updates from execution evidence; (ii) harness-benefit, the capability to benefit from updated harnesses during task solving.<n>Our analysis reveals two findings. First, harness-updating is flat in base capability: models from different capability tiers produce harness updates that lead to surprisingly similar gains.<n>Second, harness-benefit is non-monotonic in base capability: weak-tier models benefit little from updated harnesses, mid-tier models benefit most, and strong-tier models benefit less than mid-tier.
  arXiv  Detail & Related papers  (2026-05-28T22:16:14Z)
• It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers [0.0]
  A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability.<n>We test this hypothesis through a controlled 432-run experiment crossing six models across four capability tiers.<n>We introduce a six-label failure taxonomy showing that format_violation dominates capable-model failures while wrong_file dominates low-capability failures.
  arXiv  Detail & Related papers  (2026-05-26T09:08:41Z)
• LLM-driven design of physics-constrained constitutive models: two agents are better than one [0.0]
  We introduce the first multi-agent LLM-driven approach for model generation.<n>A Creator agent proposes a model tailored to the data, while an Inspector agent audits each proposal against nine physical constraints.<n>We demonstrate this concept with artificial neural networks (CANNs) and benchmark it on brain tissue, experimental rubber, and synthetic rubber.
  arXiv  Detail & Related papers  (2026-05-22T15:27:09Z)
• RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning [63.432969627395686]
  RefineRL is a novel approach designed to unleash the self-refinement capabilities of large language models for competitive programming problems.<n>Skeptical-Agent is an iterative self-refinement agent equipped with local execution tools to validate generated solutions against public test cases of CP problems.<n>A reinforcement learning solution incentivizes LLMs to self-refine with only standard RLVR data.
  arXiv  Detail & Related papers  (2026-04-01T11:54:57Z)
• Boosting LLM Reasoning via Spontaneous Self-Correction [43.4980625253775]
  One of the approaches for improving math reasoning is self-correction.<n>Existing self-correction approaches treat corrections as standalone post-generation refinements.<n>We propose SPOC, a spontaneous self-correction approach that enables LLMs to generate interleaved solutions and verifications in a single inference pass.
  arXiv  Detail & Related papers  (2025-06-07T21:23:00Z)
• IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models [11.075423190298686]
  Large language models (LLMs) are notoriously vulnerable to biases in their dataset, leading to issues such as toxicity.<n>In this paper, we introduce a novel dynamic slicing-based intent-aware LLM repair strategy, IRepair.<n>We show that IRepair repairs errors 43.6% more effectively while causing 46% less disruption to general performance.
  arXiv  Detail & Related papers  (2025-02-10T22:07:02Z)
• Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization [53.93621974137829]
  Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs.<n>EVOLVE is a framework for eliciting and tracking the evolution of Self-Refinement through iterative training.<n>We demonstrate the potential of leveraging Self-Refinement to achieve broader Self-Improvement of intrinsic model abilities.
  arXiv  Detail & Related papers  (2025-02-08T15:21:55Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.