Code as Agent Harness
Auteurs : Xuying Ning, Katherine Tieu, Dongqi Fu, Tianxin Wei, Zihao Li, Yuanchen Bei, Jiaru Zou, Mengting Ai, Zhining Liu, Ting-Wei Li, Lingjie Chen, Yanjun Zhao, Ke Yang, Bingxuan Li, Cheng Qian, Gaotang Li, Xiao Lin, Zhichen Zeng, Ruizhong Qiu, Sirui Chen, Yifan Sun, Xiyuan Yang, Ruida Wang, Rui Pan, Chenyuan Yang, Dylan Zhang, Liri Fang, Zikun Cui, Yang Cao, Pan Chen, Dorothy Sun, Ren Chen, Mahesh Srinivasan, Nipun Mathur, Yinglong Xia, Hong Li, Hong Yan, Pan Lu, Lingming Zhang, Tong Zhang, Hanghang Tong, Jingrui He
Résumé scientifique
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control and optimization that make harness reliable and adaptive. Third, we discuss scaling the harness from single-agent systems to multi-agent settings, where shared code artifacts support multi-agent coordination, review, and verification. Across these layers, we summarize representative methods and practical applications of code as agent harness, spanning coding assistants, GUI/OS automation, embodied agents, scientific discovery, personalization and recommendation, DevOps, and enterprise workflows. We further outline open challenges for harness engineering, including evaluation beyond final task success, verification under incomplete feedback, regression-free harness improvement, consistent shared state across multiple agents, human oversight for safety-critical actions, and extensions to multimodal environments. By centering code as the harness of agentic AI, this survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
Les articles autour de lui, par date et par proximité
Plus haut, c’est plus proche de cet article ; à gauche, c’est plus ancien. Les traits relient les articles proches entre eux : les groupes de traits sont des sous-thèmes. Sélectionnez un point pour voir pourquoi il est là. Retour au résumé de cet article
Les articles autour de celui-ci
Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.
Les articles les plus proches
-
Harness Engineering for AI Coding Agents: Emerging Practices and PrinciplesHua Zheng, Cheng Wen, Muhammad Sadiq et al. · 2026 · 2026 10th International Conference on Electronic Information Technology and Computer Engineering (EITCE) · Pas encore résumé
Résumé scientifique
As LLM-based coding agents transition from research prototypes to production tools, practitioners are discovering that system reliability depends less on model capability than on the engineering of the surrounding environment. A nascent discipline, harness engineering, has emerged to address this gap, encompassing the design of constraints, feedback loops, context management strategies, and verification mechanisms that govern how coding agents operate within real codebases. However, current knowledge remains fragmented across blog posts, technical reports, and isolated case studies, with no unified framework to guide practitioners or researchers. In this paper, we synthesize early industry p…
-
Natural-Language Agent HarnessesLinyue Pan, Lexiao Zou, Shuo Guo et al. · 2026 · Computation and Language · preprint, non relu par les pairs · cité 60 fois · Résumé IA disponible
Résumé scientifique
Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to inspect, compare, transfer, and ablate. This paper asks whether the reusable design pattern of an agent harness can be represented as an executable natural-language object. We introduce Natural-Language Agent Harnesses (NLAHs), editable documents that describe run-level harness policy, and Intelligent Harness Runtime (IHR), a shared runtime that interprets these documents into agent calls, handoffs, state updates, validation gates, and artifact contracts. Acro…
-
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and EditableRu-Han Wang, Yu-Cheng Shi, Zong-Xia Li et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 15 fois · Pas encore résumé
Résumé scientifique
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing eas…
-
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent HarnessesJiahang Lin, Shichun Liu, Chengjun Pan et al. · 2026 · Computation and Language · preprint, non relu par les pairs · cité 166 fois · Résumé IA disponible
Résumé scientifique
Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across editable components, voluminous trajectories that bury actionable signal, and edits whose effect is hard to attribute. We introduce Agentic Harness Engineering (AHE), a closed loop that addresses these challenges through three matched observability pillars: (1) component observability gives every editable harness component a file-level representation so the action space is explicit and revertible; (2) experience observability distills millions of raw trajector…
-
What makes a harness a harness: necessary and sufficient conditions for an agent harnessSanderson Oliveira de Macedo · 2026 · arXiv.org · preprint, non relu par les pairs · cité 6 fois · Pas encore résumé
Résumé scientifique
The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language model and turns it into a coding agent able to act on a repository. The usage is loose and polysemous. Sometimes the term denotes the whole product (Claude Code, Codex CLI); sometimes it denotes the evaluation scaffold that runs an agent against tasks (the SWE-bench harness); sometimes it gets conflated with an agent framework, an SDK, an IDE plugin, or an orchestrator. What is missing is a reference definition that works as an instrument, one that includes and excludes cases consistently. We build that definition through a conceptual analysis…
-
Beyond the Model: Demystifying Harness Effects in Software Engineering AgentsHai-Chuan Hu, Quan-Jun Zhang, Sheng-Cheng Yu et al. · 2026 · cité 4 fois · Pas encore résumé
Résumé scientifique
Large Language Model (LLM)-based agents are increasingly used for software engineering tasks, yet their performance is not determined by the base model alone. The agent harness substantially shapes how SE agents interact with repositories, execute actions, and validate solutions. However, the role of harness design remains insufficiently understood, especially across different models, tasks, and harness components. In this paper, we present a systematic empirical study of harness effects in SE agents. We first evaluate two representative harnesses, mini-SWE-agent and OpenCode, with ten models from two prominent open-weight model families, Qwen and DeepSeek, on three benchmarks: SWE-bench Pro…
-
From Question Answering to Task Completion: A Survey on Agent System and Harness DesignJian-Yuan Guo, Zhi-Wei Hao, Cheng-Cheng Wang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 15 fois · Pas encore résumé
Résumé scientifique
LLM-based agents mark a shift from passive question answering to active task completion: they perceive environments, invoke tools, maintain state, and act over extended horizons. As agent systems have evolved from prompt engineering to workflows and context engineering, harness engineering, and agent-native training with co-evolution, a central question has become increasingly important: where does the bottleneck in agent performance reside, in the foundation model, in the execution harness, or in the coupling between them? This survey examines LLM-based agents through a model-harness lens. We first clarify the functional definition of agents and the implementation view of an LLM-based agent…
-
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness EvolutionGui-Bin Zhang, Leo Lu, Fang-Zhou Xie et al. · 2026 · cité 17 fois · Pas encore résumé
Résumé scientifique
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model. Yet harness design remains manual, task-specific, and fundamentally unscalable. We present JIT-Agent, a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly for arbitrary off-the-shelf agentic LLMs. We formalize the agent harness as a composable, machine-generatable artifact governed by a fixed four-module protocol, and train JIT-Agent to customize harnesses for a given task at hand, repair harnesses for stable and reliab…
Les articles qui le citent
-
Harness-Zero: Harness Distillation via Agent-as-HarnessHao-Ran Ye, Yuxing Lu, Hao-Nan Dong et al. · 2026 · cité 8 fois · Pas encore résumé
Résumé scientifique
Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain tied to the harness at deployment. Because the best harness varies across domains, instances, and models, a general-purpose agent must either settle for a suboptimal shared harness or route among an ever-growing set of specialized ones. We therefore study agent harness distillation: using a domain- or instance-optimized harness as training-time guidance and transferring the behaviors it induces into model weights, so that its gains survive under a single fixed target harness. The challenge is that the two harnesses differ in action space and av…
-
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving AgentsXu-Ying Ning, Dong-Qi Fu, Tian-Xin Wei et al. · 2026 · cité 1 fois · Pas encore résumé
Résumé scientifique
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experience across extended interactions. Yet existing harnesses and their use are often tailored to environments and controlled through prompts, heuristics, or system-specific rules, making agent and harness coordination difficult to jointly optimize. We introduce EvoHarness-RL, a unified framework that separates environment-specific harness implementations from a shared policy-facing interface. EvoHarness-RL organizes external support into a Belief, Progress, and Experience (BPE) workspace and exposes four compact harness actions for accessing and updat…
-
Recurrent Harness for Agentic Continual LearningYu-Xin Xiao, Zhi-Yun Lu, Jian-Yu Wang et al. · 2026 · Pas encore résumé
Résumé scientifique
Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harness optimization. To address this, we propose ReHarness, a recurrent harness framework for agentic continual learning that complements forward read and write with backward revision under a strictly online streaming protocol. We ask what information could have been captured differently in the harness state to better inform the current instance in the stream. Specifically, after ea…
-
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM AgentsMin-hua Lin, Jun-Cheng Wu, Zi-Jun Wang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 46 fois · Pas encore résumé
Résumé scientifique
LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing model parameters. Harness self-evolution adapts such agents by updating these harnesses from execution evidence. Yet it remains unclear whether a model's base capability in task-solving predicts its capabilities in harness self-evolution: which models produce useful harness updates, and which actually benefit from them? 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…
-
Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure AttributionZhi-Yong Cao, Heng-Jie Zhu, Yong-Xin Wang et al. · 2026 · cité 1 fois · Pas encore résumé
Résumé scientifique
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However, most existing benchmarks focus on model capabilities and overall agent performance, with limited attention to the evaluation of agent harnesses. To address this gap, we introduce TraceTrial-Bench, which organizes harness reliability into seven components covering context, execution, governance, lifecycle, observability, tools, and verification. We construct 95 expert-level, mechanism-oriented tasks with executable or state-based ground truth to support semantically equivalent comparisons while preserving the nati…
Aller plus loin
Comment ces articles sont-ils trouvés ?
Nous comparons le titre et le résumé de cet article avec ceux de tous les articles résumés sur ce site, et avec les articles que Semantic Scholar recommande, ceux qu’il cite et ceux qui le citent (pour un article très cité, ses citations les plus récentes et, depuis OpenAlex, les plus citées). Parmi les travaux antérieurs et les suites, les articles qui s’utilisent en profondeur, une méthode qu’il utilise et les suites très citées remontent un peu. Les niveaux (très proche, proche, apparenté) viennent de la similarité des textes, pas d’un jugement de qualité ; * signale un article sans résumé, comparé par son titre. La phrase sous un article est écrite par une IA à partir des deux résumés : vérifiez-la dans les articles. Un article jugé hors sujet par trois lecteurs quitte la liste.
Mis à jour le 31 octobre 2026.