Metraipolis › archive › dc_97c368a76013
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement — arXiv:2608.13951
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13951
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:20:28.266Z
- SHA-256 of the archived text
a92a975dd717b070692c83184ca776e150028bb9653a947b532e1be55e46dbb1- Stable URL of this page
https://metraipolis.com/documento/dc_97c368a76013
How to cite
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement — arXiv:2608.13951 — arXiv (en), https://arxiv.org/abs/2608.13951 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97c368a76013 (Metraipolis archive dc_97c368a76013, sha256 a92a975dd717b070692c83184ca776e150028bb9653a947b532e1be55e46dbb1)
BibTeX
@misc{dc97c368a76013,
title = {HELIX: Model-Harness Co-evolution for Recursive Self-Improvement — arXiv:2608.13951},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13951},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97c368a76013; sha256 a92a975dd717b070692c83184ca776e150028bb9653a947b532e1be55e46dbb1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13951. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.13951 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T02:02:02.752Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).