Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

• URL: http://arxiv.org/abs/2605.30621v1
• Date: Thu, 28 May 2026 22:16:14 GMT
• Title: Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
• Abstract summary: 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.
• Score: 82.27610290890475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution adapts such agents by updating these harnesses from execution evidence. Yet it remains unclear whether a model's base capability in task-solving predicts its capabilities in harness self-evolution: which models produce useful harness updates, and which actually benefit from them? 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. 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; even Qwen3.5-9B's updates yield gains comparable to those of Claude Opus~4.6. 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. We trace low gains at the weak tier to two failure modes: weak-tier models may fail to activate relevant harness artifacts, or activate them but fail to follow them faithfully. These findings suggest investing capability budget in the task-solving agent rather than the evolver, and targeting harness invocation and long-horizon instruction following in agent training. Our source code is publicly available at https://github.com/A-EVO-Lab/a-evolve/tree/release/harness-evolution.

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)
• EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? [83.21711423118768]
  EVOHARNESSBENCH is a benchmark for evaluating agents under controlled harness evolution.<n>It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks.
  arXiv  Detail & Related papers  (2026-09-03T03:24:02Z)
• 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)
• HELIX: Model-Harness Co-evolution for Recursive Self-Improvement [8.484282837156933]
  We present HELIX, a source-traceable substrate for harness evolution.<n>We show how harness evolution expands current capability and creates learning signal for the next model.
  arXiv  Detail & Related papers  (2026-08-14T04:44:53Z)
• 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)
• Self-Evolving Embodied Agents via Skill-Harness Evolution [53.307052568223945]
  Embodied agents are increasingly built as systems around foundation models.<n>While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs.<n>We propose SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen.
  arXiv  Detail & Related papers  (2026-08-11T18:55:58Z)
• HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry [35.87794858139959]
  HarnessX is a foundry for composable, adaptive, and evolvable agent harnesses.<n>It assembles typed harness primitives via a substitution algebra, adapts them through AEGIS.<n>It closes the harness-model loop by turning trajectories into both harness updates and model training signal.
  arXiv  Detail & Related papers  (2026-06-12T08:27:11Z)
• SIA: Self Improving AI with Harness & Weight Updates [0.0]
  Humans are the bottleneck in building and improving AI.<n>We propose SIA, a self-improving loop in which a language-model agent updates both the harness and the weights of a task-specific agent.
  arXiv  Detail & Related papers  (2026-05-26T16:55:46Z)
• DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations [12.048713464721665]
  DemoEvolve is a demonstration-bootstrapped approach to harness evolution.<n>We study this paradigm as a form of sample-efficient fast adaptation.<n>We show that DemoEvolve produces more effective and auditable harness edits.
  arXiv  Detail & Related papers  (2026-05-23T12:10:52Z)
• Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning [8.33682726719781]
  In-time harnesses substantially improve large language models on complex reasoning tasks.<n>We introduce emphOn-Policy Harness Self-Distillation (OPHSD)<n>OPHSD internalizes task-specific harness capabilities into the student model.
  arXiv  Detail & Related papers  (2026-05-09T07:06:37Z)
• Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation [58.3773038915023]
  Continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge.<n>Most existing approaches treat continual learning as avoiding interference with past updates, rather than considering what properties make the current task-specific update naturally preserve previously acquired knowledge.<n>We address this problem using a projected first-order method compatible with standard deep-dots used in vision-language models.
  arXiv  Detail & Related papers  (2026-01-31T13:27:02Z)
• ThetaEvolve: Test-time Learning on Open Problems [110.5756538358217]
  We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time.<n>We find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines.
  arXiv  Detail & Related papers  (2025-11-28T18:58:14Z)
• EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards [52.42920996842378]
  We propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model.<n>This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning.<n>Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM.
  arXiv  Detail & Related papers  (2025-11-20T18:59:54Z)
• Is Self-Repair a Silver Bullet for Code Generation? [68.02601393906083]
  Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost performance. We analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS.
  arXiv  Detail & Related papers  (2023-06-16T15:13:17Z)

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.