Metraipolis › archive › dc_339142f346f0

The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks — arXiv:2611.07461

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07461
License (as archived)
CC0-1.0
Archived
2026-11-06T14:41:26.197Z
SHA-256 of the archived text
c25f7769c682ab61b0ad0535e9f22ef67aa18dbadb8408557acf95214187e347
Stable URL of this page
https://metraipolis.com/documento/dc_339142f346f0

How to cite

The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks — arXiv:2611.07461 — arXiv (en), https://arxiv.org/abs/2611.07461 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_339142f346f0 (Metraipolis archive dc_339142f346f0, sha256 c25f7769c682ab61b0ad0535e9f22ef67aa18dbadb8408557acf95214187e347)
BibTeX
@misc{dc339142f346f0,
  title = {The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks — arXiv:2611.07461},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07461},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_339142f346f0; sha256 c25f7769c682ab61b0ad0535e9f22ef67aa18dbadb8408557acf95214187e347},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07461. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal-Bench 4.0, GPT-5.6 Sol with Codex resolves 37.3% of the tasks and Claude Opus 5 with Claude Code 51.8%. These tasks fail at the step from reaching a resource to applying it, which we call the last mile to the real world. Existing approaches put the resource within reach but leave the competence to apply it with the caller, so each harness rebuilds that competence. We introduce agent-native primitives, reusable units that equip a resource with a resident LLM that applies it in context and communicates with other primitives, and HEELO (Harness Engineering around Evolving Agent-Native Primitives for the Last Mile to Real-WOrld Tasks), a harness engineering framework that builds each task's harness from a library of such primitives. HEELO composes the primitives a task needs into a task-specific graph, verifies the result against evidence from the environment, revises the primitives a failure implicates, and admits new or improved primitives after validation. We instantiate HEELO with eight primitive families, each built for one kind of task, and evaluate them on more than twenty benchmarks. Dev-Primitives raise Terminal-Bench 4.0 resolution from 37.3% under Codex to 55.5% on the same backbone, Harness Primitives composed per task raise Terminal-Bench 2.0 Pass@1 from 60.0% for the seed harness to 72.2%, Tool Primitives raise ToolBench pass rate from 55.8% to 75.1%, and Navigation Primitives raise GAIA-Text-103 accuracy from 45.6% to 58.3%. On the 46 real-world tasks of our this http URL platform, Claude Opus 5.5 with Claude Code and GPT-6.1 Sol with Codex complete 9 each on their own and 39 and 35 when connected to HEELO through our MCP server, with 1.9$\times$ and 2.3$\times$ less time and 1.55$\times$ lower cost per completed task.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.07461 — 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 2026-11-06T14:18:27.667Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).