# Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows

arXiv: https://arxiv.org/abs/2605.27922 · HTML: https://mlsanity.com/paper/2605.27922/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 18 of 18)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation](https://mlsanity.com/paper/2510.11977/) (2025)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [ClawBench: Can AI Agents Complete Everyday Online Tasks?](https://mlsanity.com/paper/2604.08523/) (2026)
- [ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents](https://mlsanity.com/paper/2604.23781/) (2026)

## Built on by (most cited first, 30 of 57)

- [Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading](https://mlsanity.com/paper/2607.08964/) (2026)
- [HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?](https://mlsanity.com/paper/2609.01437/) (2026)
- [Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?](https://mlsanity.com/paper/2608.04828/) (2026)
- [HarnessOpt-Bench: Evaluating LLMs at Harness Optimization](https://mlsanity.com/paper/2608.06301/) (2026)
- [Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses](https://mlsanity.com/paper/2608.08466/) (2026)
- [AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses](https://mlsanity.com/paper/2608.12307/) (2026)
- [Harness Continual Learning: Continual Adaptation Beyond Model Parameters](https://mlsanity.com/paper/2608.19013/) (2026)
- [Harness-Zero: Harness Distillation via Agent-as-Harness](https://mlsanity.com/paper/2609.24974/) (2026)
- [Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development](https://mlsanity.com/paper/2608.13417/) (2026)
- [RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions](https://mlsanity.com/paper/2606.03889/) (2026)
- [Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution](https://mlsanity.com/paper/2608.08311/) (2026)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering](https://mlsanity.com/paper/2608.28281/) (2026)
- [Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results](https://mlsanity.com/paper/2607.20090/) (2026)
- [HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety](https://mlsanity.com/paper/2608.17597/) (2026)
- [Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence](https://mlsanity.com/paper/2609.04518/) (2026)
- [The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI](https://mlsanity.com/paper/2607.06906/) (2026)
- [Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents](https://mlsanity.com/paper/2608.08793/) (2026)
- [Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design](https://mlsanity.com/paper/2608.10299/) (2026)
- [Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations](https://mlsanity.com/paper/2608.17433/) (2026)
- [AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents](https://mlsanity.com/paper/2609.05446/) (2026)
- [BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure](https://mlsanity.com/paper/2609.11028/) (2026)
- [Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts](https://mlsanity.com/paper/2609.18366/) (2026)
- [DeltaSelect: Affordable A/B Testing for Coding Agents](https://mlsanity.com/paper/2609.19607/) (2026)
- [Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes](https://mlsanity.com/paper/2609.36777/) (2026)
- [Finding the Right Fit: Model-Harness Interactions across Agent Tasks](https://mlsanity.com/paper/2610.00917/) (2026)
- [Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite](https://mlsanity.com/paper/2610.02826/) (2026)
- [Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI](https://mlsanity.com/paper/2607.02873/) (2026)
- [Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving](https://mlsanity.com/paper/2609.04748/) (2026)
- [Studying Without a Syllabus: Task-Agnostic Environment Preprocessing](https://mlsanity.com/paper/2609.10824/) (2026)

## Abstract (arXiv)

LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that manages context, tools, state, constraints, permissions, tracing, and recovery. However, existing benchmarks typically abstract away execution, compare complete agent systems, or hold the harness fixed, making execution-layer variation difficult to study. We introduce Harness-Bench, a diagnostic benchmark for evaluating configuration-level harness effects in realistic agent workflows. Harness-Bench evaluates representative harness configurations across multiple model backends under shared task environments, budgets, and evaluation protocols, while preserving each harness's native execution behavior. The benchmark contains 106 sandboxed offline tasks constructed from practical agent-use patterns and manually reviewed for realism, solvability, oracle-checkability, and integrity. Each run records final artifacts, execution traces, usage statistics, and validator outputs, enabling analysis beyond final completion. Across 5,194 execution trajectories, we observe substantial variation in completion, process quality, efficiency, and failure behavior across model-harness pairings. These results suggest that agent capability should be reported at the model-harness configuration level rather than attributed to the base model alone. Our analysis further identifies recurring execution-alignment failures, where plausible reasoning becomes decoupled from tool feedback, workspace state, evidence, or verifiable output contracts. Harness-Bench provides a reproducible foundation for diagnosing and improving reliable, efficient, and auditable agent execution stacks.