Metraipolis › archive › dc_db786c0d6014
HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents — arXiv:2608.02650
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02650
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:15:24.335Z
- SHA-256 of the archived text
83c4d890aed00c3663f1b0cfd95c917135017c3901f0781fb580247375a32864- Stable URL of this page
https://metraipolis.com/documento/dc_db786c0d6014
How to cite
HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents — arXiv:2608.02650 — arXiv (en), https://arxiv.org/abs/2608.02650 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db786c0d6014 (Metraipolis archive dc_db786c0d6014, sha256 83c4d890aed00c3663f1b0cfd95c917135017c3901f0781fb580247375a32864)
BibTeX
@misc{dcdb786c0d6014,
title = {HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents — arXiv:2608.02650},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02650},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db786c0d6014; sha256 83c4d890aed00c3663f1b0cfd95c917135017c3901f0781fb580247375a32864},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02650. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains challenging due to the limitations of implicit reasoning and the evolving nature of real-world execution environments. Existing tool-use agents typically rely on LLMs to infer tool compositions from textual descriptions, which can lead to inefficient exploration and unreliable execution in complex tasks. To address these challenges, we model tool relations at the schema level and construct a directed Tool--Schema Hypergraph, in which tools are represented as hyperedges from their required input-schema nodes to their output-schema nodes. Furthermore, we propose HyperAgent, a Tool--Schema Hypergraph-guided framework for dynamic planning and execution. Given a task, HyperAgent first extracts a task-relevant tool context graph and uses it to guide the construction of a schema-aware Task DAG. During execution, HyperAgent dynamically realizes each subtask by constructing a state-conditioned tool support graph through deficit-oriented expansion, which identifies unresolved requirements and retrieves supporting producer tools according to the current agent state. Experiments on AppWorld demonstrate that HyperAgent improves task completion performance while reducing redundant API calls, LLM interactions, and token consumption compared with existing agent baselines. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.02650 — 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 2026-10-31T12:05:52.724Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).