TTHE: Test-Time Harness Evolution

• URL: http://arxiv.org/abs/2607.08124v1
• Date: Thu, 09 Jul 2026 05:53:39 GMT
• Title: TTHE: Test-Time Harness Evolution
• Abstract summary: Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
• Score: 50.26245555541721
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time. This limits adaptation when the test distribution, failure modes, or tool interactions differ from those seen during development. We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs. We introduce Test-Time Harness Evolution (TTHE), which treats the executable harness as the state of test-time adaptation. During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces, without gold labels or task-specific supervision; a judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs. Crucially, TTHE does not update model weights, require gold labels, or train a separate adaptation model: solver, proposers, and judge are different roles and harnesses around the same frozen LLM, so all adaptation occurs through changes to the surrounding program. Across text-to-SQL, competitive programming, software engineering, data-science coding, and agentic tool-use tasks, TTHE improves fixed ReAct-style baseline harnesses, yielding persistent, inspectable improvements rather than a pre-searched workflow or per-query retries. These results recast test-time adaptation for LLM agents as evolution over executable control programs and identify execution-derived proxy reliability as a central challenge for robust unsupervised agent improvement.

Related papers

• 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)
• Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection [51.39973047614183]
  We present a novel approach to efficient LLM harness optimization through adaptive validation task selection.<n>$textbfTask-CoEvolve$, which co-evolves the validation tasks with the harness by addressing two challenges: selecting informative tasks and estimating full-set performance from partial evaluations.
  arXiv  Detail & Related papers  (2026-08-20T15:24:54Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• 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)
• GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science [39.146761527401424]
  GRACE-DS is a Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents.<n>It exposes agents to realistic workflow stages, from planning and data inspection through feature engineering, model development, validation, and code repair to final submission.<n>These results establish GRACE-DS as a robust platform for assessing the capacity of LLM-based AutoML agents to execute machine learning under production-like conditions.
  arXiv  Detail & Related papers  (2026-06-14T19:58:06Z)
• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws [12.757205456771295]
  This paper proposes HarnessFix, a trace-guided framework for diagnosing agent failures and repairing agent harnesses.<n> HarnessFix compiles raw execution traces and harness code into a Harness-aware Trace Intermediate Representation.<n>It attributes failures to responsible trajectory steps and harness layers, consolidates recurring diagnoses into actionable flaw records, and maps them to scoped repair operators.
  arXiv  Detail & Related papers  (2026-06-04T15:58:30Z)
• Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference [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-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows [18.6534256358905]
  We introduce Harness-Bench, a diagnostic benchmark for evaluating configuration-level harness effects in realistic agent systems.<n>The benchmark contains 106 sandboxed offline tasks constructed from practical agent-use patterns.<n>Across 5,194 execution trajectories, we observe substantial variation in completion, process quality, efficiency, and failure behavior.
  arXiv  Detail & Related papers  (2026-05-27T03:47:35Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration [68.89572566071575]
  ETAgent is a training framework for calibrating agent's tool-use behavior.<n>It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors.
  arXiv  Detail & Related papers  (2026-01-11T11:05:26Z)
• AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering [8.201374511929538]
  AgentDevel is a release engineering pipeline that iteratively runs the current agent.<n>It produces implementation-blind, symptom-level quality signals from execution traces.<n>It aggregates dominant symptom patterns and produces auditable engineering specifications.
  arXiv  Detail & Related papers  (2026-01-08T05:49:01Z)

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.