# HERO: Harnessing Evidence for Test-time Refinement and Prompt Optimization in Program Generation

arXiv: https://arxiv.org/abs/2610.19184 · HTML: https://mlsanity.com/paper/2610.19184/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (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)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (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)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [StreamBench: Towards Benchmarking Continuous Improvement of Language Agents](https://mlsanity.com/paper/2406.08747/) (2024)
- [ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?](https://mlsanity.com/paper/2407.14044/) (2024)
- [StraGo: Harnessing Strategic Guidance for Prompt Optimization](https://mlsanity.com/paper/2410.08601/) (2024)
- [DSCodeBench: A Realistic Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2505.15621/) (2025)
- [CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era](https://mlsanity.com/paper/2412.18702/) (2024)

## Abstract (arXiv)

Harness optimization improves LLMs by refining reusable prompts and scaffolding, yet requires further adaptation for program generation tasks such as text-to-SQL and text-to-Python. Existing methods often rely on LLM reflectors to propose harness updates, which can fix observed failures but also disrupt previously correct behavior. Text-to-code tasks offer a natural way to mitigate this issue: we can execute generated outputs, allowing us to evaluate and verify the effects of proposed updates directly. Building on this signal, we introduce textscHERO (Harnessing Evidence for Refinement and Optimization), which combines offline and test-time harness optimization. At the first stage, method learns reusable prompt updates from execution-verified successes and failures and validates candidate revisions before adoption. At test time, we treat the generated code as an instance-specific harness and refine it using execution feedback. Across four SQL, Cypher, and Python benchmarks, method achieves the best offline performance, improving pass@1 by (7.6) points over the initial prompt, while test-time refinement adds another (2.0) points and improves execution efficiency.