# HELIX: Model-Harness Co-evolution for Recursive Self-Improvement

arXiv: https://arxiv.org/abs/2608.13951 · HTML: https://mlsanity.com/paper/2608.13951/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [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)
- [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)
- [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)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments](https://mlsanity.com/paper/2501.10893/) (2025)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry](https://mlsanity.com/paper/2606.14249/) (2026)
- [Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops](https://mlsanity.com/paper/2607.07663/) (2026)
- [Recursive Harness Self-Improvement](https://mlsanity.com/paper/2607.15524/) (2026)
- [CLI-Anything: Towards Agent-Native Computer Use](https://mlsanity.com/paper/2606.03854/) (2026)

## Built on by (most cited first, 7 of 7)

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents](https://mlsanity.com/paper/2609.17523/) (2026)
- [Aspire: Can Models Self-Evolve from Vague Goals?](https://mlsanity.com/paper/2608.31111/) (2026)
- [RobustSGPO: Search-Space Control for Agent Harness Evolution](https://mlsanity.com/paper/2609.09646/) (2026)
- [More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses](https://mlsanity.com/paper/2609.35873/) (2026)
- [Recursive Self-Improvement through Multi-Agent Self-Supervision](https://mlsanity.com/paper/2610.12176/) (2026)
- [Harness^2: Recursive Agent Harnessing for an Open World](https://mlsanity.com/paper/2610.14224/) (2026)

## Abstract (arXiv)

Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model can accomplish and the trajectories from which it learns. This coupling motivates model-harness co-evolution for recursive self-improvement: build harnesses for a fixed model, update the model from verified sibling trajectories, and rebuild the harnesses as model capabilities change. Realizing this loop requires a controlled way to evolve harnesses while preserving intervention identity and effect. We present HELIX, a source-traceable substrate for harness evolution. HELIX decomposes agent systems into typed ports, reusable atoms, recipes, product shells, and runtime policies. It makes interventions explicit and auditable while retaining trajectories, test outcomes, and provenance. Harness evolution thus serves two linked roles: improving fixed-model execution and producing matched successes, regressions, near misses, and alternative solutions as data for subsequent model improvement. We evaluate HELIX in one evolution round on code repair. A 65-candidate portfolio discovers a fixed harness that improves task coverage by 4.0% over Pi, while the full portfolio exposes up to 58.0% more verified coverage through complementary sibling behavior. Selected candidates are assessed with repeated runs and the SWE-bench evaluator. A 200-slot sibling slice yields 438 verified SFT, critic, filter, and preference records. These results show how harness, model, and data form a feedback system: harness evolution expands current capability and creates learning signal for the next model; model updates motivate the next round of harness evolution. HELIX provides an auditable interface for studying this recursive process. Code is available at https://github.com/HKUDS/HELIX.