# TTHE: Test-Time Harness Evolution

arXiv: https://arxiv.org/abs/2607.08124 · HTML: https://mlsanity.com/paper/2607.08124/

## Key facts

- Cited by 16 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 35 of its 42 references that are in the map.
- First posted on arXiv 9 Jul 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 35)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [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)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)

## Built on by (most cited first, 16 of 16)

- [Recursive Harness Self-Improvement](https://mlsanity.com/paper/2607.15524/) (2026)
- [RRSI: Regularized Recursive Self-Improvement of Agent Harnesses](https://mlsanity.com/paper/2609.24972/) (2026)
- [Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection](https://mlsanity.com/paper/2608.20169/) (2026)
- [A Theory of Reliable Self-Evolution for Agent Harnesses](https://mlsanity.com/paper/2609.08175/) (2026)
- [ADIAS: Automated Design of Interactive Agentic Systems](https://mlsanity.com/paper/2608.06410/) (2026)
- [CineForge: Self-Improving Agents for Long-Horizon Video Generation](https://mlsanity.com/paper/2608.29621/) (2026)
- [More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses](https://mlsanity.com/paper/2609.35873/) (2026)
- [VERSE: Verified Self-Evolving Optimizer for Agent Harnesses](https://mlsanity.com/paper/2610.02616/) (2026)
- [Recursive Self-Improvement through Multi-Agent Self-Supervision](https://mlsanity.com/paper/2610.12176/) (2026)
- [Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring](https://mlsanity.com/paper/2609.33123/) (2026)
- [JET: Judge-Guided Evolution at Test Time for Agent Programs](https://mlsanity.com/paper/2609.34126/) (2026)
- [Harness Learning Enables Generalizable Test-Time Adaptation](https://mlsanity.com/paper/2609.35738/) (2026)
- [ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization](https://mlsanity.com/paper/2610.00906/) (2026)
- [FreeEvolve: Learning to Evolve Beyond Fixed Loops](https://mlsanity.com/paper/2610.09197/) (2026)
- [Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds](https://mlsanity.com/paper/2610.11552/) (2026)
- [Harness^2: Recursive Agent Harnessing for an Open World](https://mlsanity.com/paper/2610.14224/) (2026)

## Abstract (arXiv)

The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches typically optimize harnesses on training or development data and freeze the resulting programs at test time, limiting adaptation to shifts in task distributions, failure modes, and tool interactions. We ask whether the harness can instead be optimized during evaluation using unlabeled execution traces. We introduce Test-Time Harness Evolution (TTHE), which treats the executable harness as the state of test-time adaptation. On each unlabeled test batch, TTHE iteratively evolves a population of candidate harnesses through agentic proposers that reason over execution traces and explore diverse edit directions. A judge selects a candidate using execution traces and execution-derived proxy signals. The selected harness determines the current batch's outputs and initializes adaptation on the next. Crucially, the solver, proposers, and judge operate through different harnesses around the same frozen LLM, without weight updates, access to final-answer labels, or a separately trained adaptation model. Across six execution-grounded benchmarks spanning text-to-SQL, competitive programming, software engineering, data-science coding, terminal-based tasks, and agentic tool use, TTHE improves fixed ReAct-style baseline harnesses through persistent, inspectable program adaptation. These results recast test-time adaptation for LLM agents as evolution over executable control programs and identify execution-derived proxy reliability as a central challenge for robust unsupervised agent improvement.