DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations

• URL: http://arxiv.org/abs/2605.24539v1
• Date: Sat, 23 May 2026 12:10:52 GMT
• Title: DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations
• Abstract summary: 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.
• Score: 12.048713464721665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, an agent can acquire task-specific competence by changing its external harness, while leaving the base model's general capabilities intact. Prior work shows that self-generated rollouts can support harness search, suggesting that agents may acquire new task competence through practice. Yet in long-horizon stochastic environments, self-practice becomes fragile: rewards are sparse, outcomes are high-variance, and failures are hard to attribute to concrete harness mechanisms. We introduce DemoEvolve, a demonstration-bootstrapped approach to harness evolution. When reward-only search is too broad and noisy, competent human trajectories serve as expert reference experience for the coding proposer, guiding harness-level diagnosis and editing. Experiments on Liar's Dice show that self-rollout evolution can work when episodes are short and failures are attributable. In contrast, Balatro exposes a harder long-horizon stochastic regime, where self-rollout evolution is misled by sparse feedback and candidate-selection noise, while tutorial-like textual knowledge alone does not yield stable improvement. Under the same limited budget, DemoEvolve produces more effective and auditable harness edits and achieves better performance. Overall, demonstrations make sparse-feedback harness evolution more diagnosable, localizable, and stable.

Related papers

• ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement [46.36989489677189]
  We propose a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution.<n> ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies.<n>It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection.
  arXiv  Detail & Related papers  (2026-09-14T00:10:45Z)
• Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents [25.41577484327689]
  Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents.<n>Existing harness evolution methods rely on iterative search, repeatedly evaluating and revising candidate harnesses.<n>We propose Ecdysis, an efficient and effective framework that distinguishes model-specific accommodation from systematic harness deficiencies.
  arXiv  Detail & Related papers  (2026-09-10T15:09:08Z)
• 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)
• HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution [11.431479238875712]
  We introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution.<n>We conduct extensive experiments on several benchmarks spanning open-domain and enterprise scenarios, using different models and agent frameworks.<n>Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all benchmarks and settings.
  arXiv  Detail & Related papers  (2026-09-01T07:31:18Z)
• Aspire: Can Models Self-Evolve from Vague Goals? [61.65007006747275]
  We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution.<n>ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment.<n>Our experiments show that vague goals redirect search effort toward goal interpretation.
  arXiv  Detail & Related papers  (2026-08-31T17:14:59Z)
• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents [67.97365535829098]
  Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.<n>We propose Evo-Harness, which distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation.<n>Our analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly.
  arXiv  Detail & Related papers  (2026-08-15T06:43:56Z)
• 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)
• Harnessing Agentic Evolution [32.567492765277855]
  Agentic evolution is a powerful paradigm for improving programs, iteration, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search.<n>Existing methods are typically instantiated either as fixed hand-designed procedures that are modular but rigid, or as general-purpose agents that flexibly integrate feedback but can drift in long-horizon evolution.<n>We introduce AEvo, a harnessed meta-editing framework in which a meta-agent observes this state and acts not by directly proposing the next candidate, but by editing the procedure or agent context that controls future evolution.
  arXiv  Detail & Related papers  (2026-05-13T17:45:16Z)
• SEIF: Self-Evolving Reinforcement Learning for Instruction Following [53.280277743734096]
  We propose SEIF (Self-Evolving Reinforcement Learning for Instruction Following), a self-evolving framework for enhancing the instruction-following ability of large language models (LLMs)<n>SEIF forms a closed self-evolution loop that improves the model's instruction-following ability, where instruction difficulty evolution and model capability evolution reinforce each other.<n> Experiments across multiple model scales and architectures show that SEIF consistently improves instruction-following performance, suggesting strong generality.
  arXiv  Detail & Related papers  (2026-05-08T09:13:12Z)
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses [57.20181537213498]
  Agentic Harness Engineering (AHE) is a closed loop that automates harness engineering.<n>AHE addresses challenges through three matched observability pillars.<n>Ten AHE lift pass@1 on Terminal-Bench 2 from 69.7% to 77.0%, surpassing the human-designed harness Codex-CLI.<n>On SWE-bench-verified it tops aggregate success at 12% fewer tokens than the seed, and on Terminal-Bench 2 it yields +5.1 to +10.1pp cross-family gains.
  arXiv  Detail & Related papers  (2026-04-28T16:55:02Z)
• Self-Consolidation for Self-Evolving Agents [51.94826934403236]
  Large language model (LLM) agents operate as static systems, lacking the ability to evolve through lifelong interaction.<n>We propose a novel self-evolving framework for LLM agents that introduces a complementary evolution mechanism.
  arXiv  Detail & Related papers  (2026-02-02T11:16:07Z)
• Guided Self-Evolving LLMs with Minimal Human Supervision [53.111086364268566]
  Unguided self-evolving systems often plateau quickly or degrade as training.<n>R-Few is a guided Self-Play Challenger acquirer framework that incorporates lightweight human oversight through in-context grounding and mixed training.<n>R-Few achieves consistent and iterative improvements across math and general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-12-02T07:06:11Z)
• Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents [58.69865074060139]
  We study the case where an agent's self-evolution deviates in unintended ways, leading to undesirable or even harmful outcomes.<n>Our empirical findings reveal that misevolution is a widespread risk, affecting agents built even on top-tier LLMs.<n>We discuss potential mitigation strategies to inspire further research on building safer and more trustworthy self-evolving agents.
  arXiv  Detail & Related papers  (2025-09-30T14:55:55Z)
• Self-Consistency as a Free Lunch: Reducing Hallucinations in Vision-Language Models via Self-Reflection [71.8243083897721]
  Vision-language models often hallucinate details, generating non-existent objects or inaccurate attributes that compromise output reliability.<n>We present a novel framework that leverages the model's self-consistency between long responses and short answers to generate preference pairs for training.
  arXiv  Detail & Related papers  (2025-09-27T10:37:11Z)
• LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning [16.093659272414527]
  We introduce Language Models for Out-of-Distribution Recovery (LaMOuR), which enables recovery learning without relying on uncertainty estimation.<n>LaMOuR generates dense reward codes that guide the agent back to a state where it can successfully perform its original task.<n> Experimental results show that LaMOuR substantially enhances recovery efficiency across diverse locomotion tasks.
  arXiv  Detail & Related papers  (2025-03-21T13:20:39Z)

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.