Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

• URL: http://arxiv.org/abs/2608.20169v2
• Date: Mon, 24 Aug 2026 02:04:24 GMT
• Title: Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
• Abstract summary: 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.
• Score: 51.39973047614183
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a novel approach to efficient LLM harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Existing approaches, however, evaluate a fixed validation set in full at every iteration, incurring substantial evaluation costs even on tasks that become less discriminative as the harness evolves. We propose $\textbf{Task-CoEvolve}$, which co-evolves the validation tasks with the harness by addressing two challenges: selecting informative tasks and estimating full-set performance from partial evaluations. Task-CoEvolve builds on the observation that tasks on which candidate harnesses disagree are more informative for distinguishing among them than tasks that are consistently solved or failed. It uses variance-weighted sampling based on past outcomes to focus evaluation on tasks near the capability frontier, with the sampling distribution adapting as the harness evolves. It then estimates full-set scores from the sampled tasks by accounting for their sampling probabilities, enabling consistent comparisons across iterations despite evaluating different subsets. Experiments on online text classification and Terminal-Bench 2.1 show that Task-CoEvolve consistently outperforms subset-based baselines and matches the final performance of full-set search while reducing the number of evaluations during optimization by 80%. Code will be released at https://github.com/Agent4Science-UTokyo/Task-CoEvolve.

Related papers

• HarnessOpt-Bench: Evaluating LLMs at Harness Optimization [3.846854817984248]
  We introduce a benchmark for end-to-end harness optimization under expensive evaluation regimes.<n>A trusted execution environment enforces the evaluation boundary, target-agent resource use, and preserves candidate versions for audit.<n>Experiment results show that models separate more than the coding harnesses they act through, native harnesses are not consistently superior, and gains vary substantially across tasks.
  arXiv  Detail & Related papers  (2026-08-06T17:21:05Z)
• Rethinking the Evaluation of Harness Evolution for Agents [83.07258924910069]
  Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark.<n>This protocol raises two fundamental concerns.<n>As in agentic test-time scaling, it should therefore be compared with simple task-level search baselines under matched feedback and inference budgets.
  arXiv  Detail & Related papers  (2026-07-14T00:18:42Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  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.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning [82.925106913459]
  Reinforcement finetuning (RFT) is a key technique for aligning Large Language Models (LLMs) with human preferences and enhancing reasoning.<n>We introduce BOTS, a unified framework for Bayesian Online Task Selection in RFT reinforcement finetuning.
  arXiv  Detail & Related papers  (2025-10-30T11:15:23Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks [40.91931801667421]
  Our paper presents a novel global-to-local algorithm that interleaves influence function as a data selection method with Bayesian optimization to optimize data mixture via feedback from a specific unseen evaluation task.<n>By analyzing DUET's cumulative regret, we theoretically show that DUET converges to the optimal training data mixture for an unseen task even without any data knowledge of the task.
  arXiv  Detail & Related papers  (2025-02-01T01:52:32Z)
• Model Predictive Task Sampling for Efficient and Robust Adaptation [57.414812940406996]
  We introduce Model Predictive Task Sampling (MPTS), a framework that bridges the task space and adaptation risk distributions.<n>MPTS employs a generative model to characterize the episodic optimization process and predicts task-specific adaptation risk via posterior inference.<n>MPTS seamlessly integrates into zero-shot, few-shot, and supervised finetuning settings.
  arXiv  Detail & Related papers  (2025-01-19T13:14:53Z)
• SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation [75.56845750400116]
  Disaggregated evaluation -- estimation of performance of a machine learning model on different subpopulations -- is a core task when assessing performance and group-fairness of AI systems. We develop SureMap that has high estimation accuracy for both multi-task and single-task disaggregated evaluations of blackbox models. Our method combines maximum a posteriori (MAP) estimation using a well-chosen prior together with cross-validation-free tuning via Stein's unbiased risk estimate (SURE)
  arXiv  Detail & Related papers  (2024-11-14T17:53:35Z)
• Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach [17.79010397902909]
  We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks.<n>This problem has broad applications in NLP, such as targeted instruction tuning and data selection in chain-of-thought fine-tuning.<n>We introduce a new algorithm for estimating model fine-tuning performance without requiring repeated training.
  arXiv  Detail & Related papers  (2024-09-28T21:26:50Z)
• Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning [6.704927458661697]
  Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the reduction in classification error, and more general costs fit in the same framework. We propose Bayesian Estimate of Mean Proper Scores (BEMPS) to estimate the increase in strictly proper scores. We show that BEMPS yields robust acquisition functions and well-calibrated classifiers, and consistently outperforms the others tested.
  arXiv  Detail & Related papers  (2023-12-15T11:02:17Z)
• Composite Learning for Robust and Effective Dense Predictions [81.2055761433725]
  Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. We find that jointly training a dense prediction (target) task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
  arXiv  Detail & Related papers  (2022-10-13T17:59:16Z)

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.