# Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

arXiv: https://arxiv.org/abs/2605.22166 · HTML: https://mlsanity.com/paper/2605.22166/

## Key facts

- Cited by 27 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 22 of its 32 references that are in the map.
- First posted on arXiv 21 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, 22 of 22)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [Distilling LLM Agent into Small Models with Retrieval and Code Tools](https://mlsanity.com/paper/2505.17612/) (2025)
- [Continual Harness: Online Adaptation for Self-Improving Foundation Agents](https://mlsanity.com/paper/2605.09998/) (2026)
- [PromptWizard: Task-Aware Prompt Optimization Framework](https://mlsanity.com/paper/2405.18369/) (2024)
- [Learning to Continually Learn via Meta-learning Agentic Memory Designs](https://mlsanity.com/paper/2602.07755/) (2026)
- [Workspace Optimization: How to Train Your Agent](https://mlsanity.com/paper/2605.09650/) (2026)
- [CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning](https://mlsanity.com/paper/2601.15141/) (2026)

## Built on by (most cited first, 27 of 27)

- [HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry](https://mlsanity.com/paper/2606.14249/) (2026)
- [RHO: Your Coding Agent is Secretly a Roboticist](https://mlsanity.com/paper/2606.16458/) (2026)
- [Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories](https://mlsanity.com/paper/2608.02276/) (2026)
- [HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution](https://mlsanity.com/paper/2607.13683/) (2026)
- [Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation](https://mlsanity.com/paper/2607.08938/) (2026)
- [Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened](https://mlsanity.com/paper/2607.13083/) (2026)
- [Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses](https://mlsanity.com/paper/2608.08466/) (2026)
- [Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails](https://mlsanity.com/paper/2609.09134/) (2026)
- [Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents](https://mlsanity.com/paper/2609.11677/) (2026)
- [LemonHarness Technical Report](https://mlsanity.com/paper/2606.24311/) (2026)
- [Self-Evolving Coding Agents](https://mlsanity.com/paper/2608.03392/) (2026)
- [HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety](https://mlsanity.com/paper/2608.17597/) (2026)
- [EvoOntology: A Self-Evolving Ontology Layer for Data Agents](https://mlsanity.com/paper/2609.15779/) (2026)
- [Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation](https://mlsanity.com/paper/2606.03137/) (2026)
- [Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents](https://mlsanity.com/paper/2607.04528/) (2026)
- [Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems](https://mlsanity.com/paper/2607.28147/) (2026)
- [StateM: Reaching 95.3% Raw Accuracy, or a 15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling](https://mlsanity.com/paper/2608.15089/) (2026)
- [MUSE: A Unified Agentic Harness for MLLMs](https://mlsanity.com/paper/2606.03005/) (2026)
- [STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control](https://mlsanity.com/paper/2608.22538/) (2026)
- [LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents](https://mlsanity.com/paper/2608.25777/) (2026)
- [Harness Engineering for Predictable Agentic Systems: An Empirical Study of Deterministic Execution Constraints](https://mlsanity.com/paper/2608.26197/) (2026)
- [Sentry: Learning to Recover from LLM Agent Failures at Test Time](https://mlsanity.com/paper/2610.02994/) (2026)
- [SHarP: Saliency-based Pruning of Agent Harnesses](https://mlsanity.com/paper/2610.04178/) (2026)
- [FreeEvolve: Learning to Evolve Beyond Fixed Loops](https://mlsanity.com/paper/2610.09197/) (2026)
- [Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning](https://mlsanity.com/paper/2610.11450/) (2026)
- [EvoBelief: Falsifiable World Models for Self-Improving LLM Agents](https://mlsanity.com/paper/2610.12789/) (2026)
- [HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems](https://mlsanity.com/paper/2610.15221/) (2026)

## Abstract (arXiv)

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights or evaluation environments. Life-Harness evolves from training trajectories by converting recurring interaction failures into reusable interventions across environment contracts, procedural skills, action realization, and trajectory regulation, and remains fixed for evaluation on unseen tasks. We evaluate Life-Harness across eight environments from AgentBench, τ-bench, τ2-bench, and AppWorld using 18 open-weight backbones, and further test three frontier models on seven environments. With Qwen3-4B-Instruct, Life-Harness exceeds Meta-Harness and AHE by 28.7 and 7.5 percentage points in mean accuracy across the seven shared environments, respectively, while using 8.5% and 68.4% fewer optimization tokens. The evolved harnesses also benefit GPT 5.5, Opus 4.8, and Gemini 3.1 Pro, yielding an average accuracy gain of 3.5 percentage points. Code is available at https://github.com/Tianshi-Xu/Life-Harness.