Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.28069

Training the Whole Agent, Not Just the Model

Lingxiao Tang·Wei Tao·Yiwen Guo·Lingfeng Bao
View original source ↗Read source document ↗Export metadata ↓

Abstract

Training coding agents typically updates the policy while keeping the harness fixed. During training, trajectories reveal flawed repair strategies and interaction problems that vary across tasks and change as the policy learns. We introduce HarnessAdapt-RL, which trains the policy and adapts its harness during reinforcement learning. For flawed repair strategies, a frozen teacher generates task-specific mechanism-level skills. For interaction problems recurring across tasks, a separate teacher model evolves tools and hooks, keeping each change only if it improves the observed pass rate or the observed trainable rate without lowering either. The policy trains with the adapted harness, and its new trajectories guide further adaptation. With a 9B base model, HarnessAdapt-RL improves pass@1 over GRPO by 9.8, 12.6, and 6.4 percentage points on SWE-bench Verified, Multilingual, and Pro, and outperforms GRPO with the human-designed OpenHands harness. Gains from mechanism-level skills persist after their removal at evaluation. Re-evolving tools and hooks as the policy changes outperforms freezing early versions. Removing them at deployment, in contrast, costs up to 7.7 percentage points. Training therefore produces a model-harness pair: the trained policy and the evolved tools and hooks, with skills removed at deployment.

Explore related subjects

cs.SE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Lingxiao Tang, Wei Tao, Yiwen Guo, Lingfeng Bao. 2026-10-20. Training the Whole Agent, Not Just the Model. https://arxiv.org/abs/2610.28069

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Mitigating Risks in Software Development through Effective Requirements Engineering

Problems that originate in requirements are common and expensive in software projects, and they are a recurring cause of late delivery, budget overruns and cancellation. This paper is a narrative overview of requirements engineering (RE) as a means of reducing these risks. It outlines the core RE activities (elicitation, analysis and negotiation, specification, validation and change management) and the kinds of statements a requirements document contains, including the distinction between requirements, domain properties, assumptions and definitions. It reviews the evidence on the cost of requirements defects, together with the main criticisms of that evidence, and compares how the waterfall, spiral, iterative (Rational Unified Process) and agile lifecycles treat requirements. It then discusses stakeholder identification, elicitation techniques and common obstacles to elicitation, and describes practical ways of turning vague or conflicting stakeholder statements, including security and performance expectations, into precise, verifiable and prioritized requirements. The paper is intended as an introduction for practitioners and students who work with requirements but are not RE specialists.

cs.SE↗
arXiv2026

WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development

Web development involves turning UI designs into functional webpages, which can be difficult for both beginners and experienced developers due to the complexity of HTML's hierarchical structures and styles. While Large Language Models (LLMs) have shown promise in generating source code, two major challenges persist in UI-to-HTML code generation: (1) effectively representing HTML's hierarchical structure for LLMs, and (2) bridging the gap between the visual nature of UI designs and the text-based format of HTML code. To tackle these challenges, we introduce Waffle, a new fine-tuning strategy that uses a structure-aware attention mechanism to improve LLMs' understanding of HTML's structure and a contrastive fine-tuning approach to align LLMs' understanding of UI images and HTML code. Models fine-tuned with Waffle show up to 9.00 pp (percentage point) higher HTML match, 0.0982 higher CW-SSIM, 32.99 higher CLIP, and 27.12 pp higher LLEM on our new benchmark WebSight-Test and an existing benchmark Design2Code, outperforming current fine-tuning methods.

cs.SE↗
arXiv2026

Can Language Models Replace Programmers for Coding? REPOCOD Says 'Not Yet'

Recently, a number of repository-level code generation benchmarks-such as CoderEval, DevEval, RepoEval, RepoBench, and LongCodeArena-have emerged to evaluate the capabilities of large language models (LLMs) beyond standalone benchmarks like HumanEval and MBPP. Thus, a natural question is, would LLMs have similar performance in real world coding tasks as their performance in these benchmarks? Unfortunately, one cannot answer this question, since these benchmarks consist of short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks. To address these challenges, we create REPOCOD, a Python code-generation benchmark containing complex tasks with realistic dependencies in real-world large projects and appropriate metrics for evaluating source code. It includes 980 whole-function generation tasks from 11 popular projects, 50.8% of which require repository-level context. REPOCOD includes 314 developer-written test cases per instance for better evaluation. We evaluate ten LLMs on REPOCOD and find that none achieves more than 30% pass@1 on REPOCOD, indicating the necessity of building stronger LLMs that can help developers in real-world software development. In addition, we found that retrieval-augmented generation achieves better results than using target function dependencies as context.

cs.SE↗