# HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

arXiv: https://arxiv.org/abs/2608.06301 · HTML: https://mlsanity.com/paper/2608.06301/

## Key facts

- Cited by 9 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 30 of its 37 references that are in the map.
- First posted on arXiv 6 Aug 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, 30 of 30)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [A Self-Improving Coding Agent](https://mlsanity.com/paper/2504.15228/) (2025)
- [Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs](https://mlsanity.com/paper/2406.16218/) (2024)
- [Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows](https://mlsanity.com/paper/2605.27922/) (2026)
- [HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry](https://mlsanity.com/paper/2606.14249/) (2026)
- [Stop Comparing LLM Agents Without Disclosing the Harness](https://mlsanity.com/paper/2605.23950/) (2026)
- [LLM-AutoDiff: Auto-Differentiate Any LLM Workflow](https://mlsanity.com/paper/2501.16673/) (2025)
- [RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement](https://mlsanity.com/paper/2607.25886/) (2026)
- [VeRO: A Harness for Agents to Optimize Agents](https://mlsanity.com/paper/2602.22480/) (2026)
- [Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack](https://mlsanity.com/paper/2605.12673/) (2026)

## Built on by (most cited first, 9 of 9)

- [HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?](https://mlsanity.com/paper/2609.01437/) (2026)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts](https://mlsanity.com/paper/2609.18366/) (2026)
- [From Migration to Calibration: Aligning Agents with Deployment Requirements](https://mlsanity.com/paper/2609.35149/) (2026)
- [Turbo Harness: Instance-Adaptive Harness Optimization](https://mlsanity.com/paper/2609.40330/) (2026)
- [What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects](https://mlsanity.com/paper/2610.05533/) (2026)
- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)
- [EvoCowork: A Benchmark for Real-World Office Tasks](https://mlsanity.com/paper/2610.14828/) (2026)
- [Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents](https://mlsanity.com/paper/2610.20344/) (2026)

## Abstract (arXiv)

As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a demanding capability for AI systems themselves. Yet the community lacks a common protocol for measuring how well frontier LLMs perform at this task. We introduce HarnessOpt-Bench, a benchmark for end-to-end harness optimization under expensive and stochastic evaluation. An optimizer, an LLM paired with a coding harness, receives a target agent's seed harness, graded evaluation feedback, and a fixed target-evaluation budget. It edits the harness and nominates a final candidate, which is scored by its normalized gain over the seed on a held-out test partition that remains inaccessible throughout search. A trusted execution environment enforces the evaluation boundary, meters target-agent resource use, and preserves candidate versions for audit. We evaluate 5 frontier LLMs as optimizers both under a shared coding harness and under their native harnesses across 4 downstream tasks, over 111 scored runs. Experiment results show that optimizer models separate more than the coding harnesses they act through, native harnesses are not consistently superior, and gains vary substantially across tasks and seed regimes. These results establish harness optimization as a measurable and discriminative capability with large space for improvement.