arXiv cs.AI· Haibo Jin, Peng Kuang, Xiaopeng Yuan, Lucheng Fu, Jerry Wang, Xucheng Yu, Yaoning Yu, Dehao Wu, Runguo Li, Colin Su, Jingxuan Sun, Xuyang Liu, Haojing Luo, Haohan Wang·· 4 小时前AI 评分54
arXiv 论文提出 agent-native primitives 与 HEELO 框架提升智能体真实任务表现
The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
AI 导读
Haibo Jin 等人的 arXiv 论文（2611.07461）提出 agent-native primitives，即可复用单元，为资源配备常驻 LLM 在上下文中应用资源并与其他 primitives 通信，并介绍 HEELO 框架，将 primitives 组合成任务特定图、依据环境证据验证并修订。
正文 · 原文
Authors:Haibo Jin, Peng Kuang, Xiaopeng Yuan, Lucheng Fu, Jerry Wang, Xucheng Yu, Yaoning Yu, Dehao Wu, Runguo Li, Colin Su, Jingxuan Sun, Xuyang Liu, Haojing Luo, Haohan Wang
Abstract: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.
| Comments: | 102 pages, 21 figures, 54 tables. Project page:this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Software Engineering (cs.SE) |
| Cite as: | arXiv:2611.07461 [cs.CL] |
| (or arXiv:2611.07461v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07461 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haibo Jin [view email]
[v1]
Thu, 5 Nov 2026 05:15:27 UTC (9,276 KB)
来源：arXiv cs.AI · arxiv.org