Metraipolis › archive › dc_bf0bf2dbdfc5

Capability-Grounded Agentic Planning — arXiv:2610.41040

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41040
License (as archived): CC0-1.0
Archived: 2026-11-02T07:18:45.229Z
SHA-256 of the archived text: 19b6f542fe8fccfcc90ce2dcca03fb0dbf8a2535d01202909b328375c39a20b2
Stable URL of this page: https://metraipolis.com/documento/dc_bf0bf2dbdfc5

How to cite

Capability-Grounded Agentic Planning — arXiv:2610.41040 — arXiv (en), https://arxiv.org/abs/2610.41040 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf0bf2dbdfc5 (Metraipolis archive dc_bf0bf2dbdfc5, sha256 19b6f542fe8fccfcc90ce2dcca03fb0dbf8a2535d01202909b328375c39a20b2)

BibTeX

@misc{dcbf0bf2dbdfc5,
  title = {Capability-Grounded Agentic Planning — arXiv:2610.41040},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41040},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf0bf2dbdfc5; sha256 19b6f542fe8fccfcc90ce2dcca03fb0dbf8a2535d01202909b328375c39a20b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41040. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by trial and error, with no guarantee of an executable plan. We present Capability-Grounded Agentic Planning (CGAP), which instead reasons about what a request requires and what tools provide. CGAP compiles the tool catalog deterministically into a PDDL model, uses an LLM to turn the request into goals, and solves the model with a classical planner. Since tool outputs are unknown in advance, the model is abstract, tracking which inputs are available, not their values. During execution, an LLM adds entity-specific calls that abstract plans omit, and deterministic checks reject any that break the plan. Every argument is drawn from a cited source, such as a conversation span or an earlier tool response, and each requested result counts as delivered only after an LLM verifier checks it against the request. With three LLMs on ToolSandbox, ComplexFuncBench, BFCL multi-turn, and $\tau^2$-bench retail, CGAP outperforms a standard tool-calling agent by up to 28.9 points.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41040 — 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 2026-11-02T07:16:57.136Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).