Paper Detail

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

Yaxin Du, Yifan Zhou, Yujie Ge, Jiajun Wang, Xianghe Pang, Shuo Tang, Tuney Zheng, Bryan Dai, Jian Yang, Siheng Chen

arxiv Score 12.3

Published 2026-06-11 · First seen 2026-06-13

General AI

Abstract

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an \emph{execution-granularity mismatch}: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce \textbf{HyperTool}, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69\% to 35.29\% on Qwen3-32B and from 9.93\% to 33.33\% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{du2026hypertool,
  title = {HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents},
  author = {Yaxin Du and Yifan Zhou and Yujie Ge and Jiajun Wang and Xianghe Pang and Shuo Tang and Tuney Zheng and Bryan Dai and Jian Yang and Siheng Chen},
  year = {2026},
  abstract = {Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an \textbackslash{}emph\{execution-granularity mismatch\}: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce \textbackslash{}textbf\{HyperTool\}, a unified executable MCP-style tool interface that changes the model-visi},
  url = {https://arxiv.org/abs/2606.13663},
  keywords = {cs.CL},
  eprint = {2606.13663},
  archiveprefix = {arXiv},
}

Metadata

{}