Living-Harness Is an Interactive-Agent Evolver

• URL: http://arxiv.org/abs/2607.26598v1
• Date: Wed, 29 Jul 2026 08:20:11 GMT
• Title: Living-Harness Is an Interactive-Agent Evolver
• Abstract summary: 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.<n>We propose $textbfLiving-Harness, a self-evolving agent harness that converts each completed trajectory and its evaluator signals into posterior evidence for bounded harness updates.
• Score: 15.081919387954578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. Static harnesses improve reliability through fixed tools, context, memory, and workflow structures, but remain unchanged after deployment. We propose $\textbf{Living-Harness}$, a self-evolving agent harness that converts each completed trajectory and its evaluator signals into posterior evidence for bounded harness updates. Guided by a domain-level $\textbf{Evolution-SOP}$ ($\textbf{S}$tandard $\textbf{O}$perating $\textbf{P}$rocedure), Living-Harness extracts an episode abstraction and structured update evidence, and writes two complementary forms of procedural knowledge: episodic memory that records trigger conditions, failure patterns, and recovery actions, and a state graph that records state nodes, repair edges, and transition rules. The updated harness state is retrieved to guide future interactions, while tools and base context remain frozen, allowing procedural repairs to accumulate across evolution cycles. On eight interactive environments derived from $τ^2$-Bench and MultiWOZ-2.4, Living-Harness improves average Pass@1 over the strongest interactive baseline by 10.07 and 9.91 percentage points, respectively, and supports retrieval-only reuse of the evolved harness state across model backbones.

Related papers

• From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents [48.50635499112162]
  We present an online skill-evolution framework that converts interaction trajectories and evaluator feedback into a persistent, versioned library of reusable procedures.<n>We compare the full evolving-library system with a configuration-matched empty-library control across four OSWorld application domains.<n>In GIMP, provenance-aware analysis reveals retrieval across task-of-origin boundaries and revision, where repeated accepted edits fail to recover the originating task.
  arXiv  Detail & Related papers  (2026-09-04T08:29:45Z)
• REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation [64.84437332310516]
  We introduce textbfREER-PT, a scalable framework that extends Reverse-Engineered Reasoning (REER) to raw pre-training data.<n>REER-PT identifies continuations that are difficult to predict but can still be inferred from the preceding context, and inserts concise reasoning annotations that reconstruct the missing connection between context and continuation.<n>This sparse transformation preserves the source text and remains compatible with standard next-token prediction, avoiding online reasoning rollouts during pre-training.
  arXiv  Detail & Related papers  (2026-08-31T11:34:19Z)
• Harness Continual Learning: Continual Adaptation Beyond Model Parameters [9.54786133734043]
  We formulate a new continual learning paradigm in which the harness evolves around a frozen foundation model.<n>A candidate commits a harness only after checking current improvement, historical retention, and validity.<n>Experiments demonstrate capability accumulation and failure recovery, with relative gains exceeding 10% over corresponding baselines in multiple settings.
  arXiv  Detail & Related papers  (2026-08-19T15:12:31Z)
• Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution [13.491535879221901]
  PMCoder is an issue-resolution agent that couples a hierarchical phase planner with episodic memory.<n>On SWE-bench Verified, PMCoder resolves an average of $25$ more cases than a harness-matched baseline.
  arXiv  Detail & Related papers  (2026-08-07T05:05:05Z)
• Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents [0.0]
  AI agents encounter learning opportunities in every episode they run, and discard nearly all of them.<n>We show that this feedback is a sufficient signal for continual learning when the frozen model is paired with an external memory.<n>We show that learning from the one-bit outcome verdict lifts single-trial success to 1.6$times$ the baseline, and learning from corrections to 2.6$times$, converting 22 of the 84 tasks the baseline never solves.
  arXiv  Detail & Related papers  (2026-07-24T10:01:00Z)
• Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift [0.0]
  We propose Graph-Regularized Agentic Context Evolution (GRACE) to maintain persistent instruction component as a typed semantic graph.<n>We evaluate GRACE within a fixed telecom agent harness derived from $2$-bench under a controlled distribution-shift protocol.
  arXiv  Detail & Related papers  (2026-07-10T08:10:37Z)
• SEAGym: An Evaluation Environment for Self-Evolving LLM Agents [30.362414820430402]
  SEAGym is an evaluation environment for measuring agent harness updates across training, validation, test, replay, and cost records.<n>It turns Harbor-compatible benchmarks into dynamic self-evolution task sources with train batches, frozen update-validation, held-out ID and OOD transfer views, replay diagnostics, and saved snapshot and metric records.
  arXiv  Detail & Related papers  (2026-06-16T05:50:55Z)
• Scaling Laws for Agent Harnesses via Effective Feedback Compute [53.68149869349268]
  emphEffective Feedback Compute (EFC) is a trace-level scaling coordinate that credits feedback only when it is informative, valid, non-redundant, and retained for subsequent decisions.<n>EFC-based coordinates consistently predict failure rates better than raw-compute baselines.
  arXiv  Detail & Related papers  (2026-05-28T09:45:47Z)
• 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)
• All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution [20.68235182577703]
  All-Mem maintains a structured memory bank via explicit, non destructive consolidation.<n>Periodically offline, an LLM diagnoser proposes confidence scored topology edits executed with three operators: SPLIT, MERGE, and UPDATE.<n>At query time, typed links enable hop bounded, budgeted expansion from active anchors to archived evidence when needed.
  arXiv  Detail & Related papers  (2026-03-20T03:14:40Z)
• OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows [9.617220633655716]
  We present textbfunderlineOmni-textbfunderlineModality textbfunderlineGeneration Agent (textbfOMG-Agent)
  arXiv  Detail & Related papers  (2026-02-04T02:25:40Z)
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution [52.76038908826961]
  We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
  arXiv  Detail & Related papers  (2025-12-11T14:40:01Z)
• Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval [50.47192086219752]
  $texttABEL$ is a simple but effective unsupervised method to enhance passage retrieval in zero-shot settings. By either fine-tuning $texttABEL$ on labelled data or integrating it with existing supervised dense retrievers, we achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2023-11-27T06:22:57Z)

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.