Metraipolis › archive › dc_76facccffda3

Robust Function Calling for LLM Agents Under Interface Drift — arXiv:2610.23342

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.23342
License (as archived): CC0-1.0
Archived: 2026-10-19T08:42:35.563Z
SHA-256 of the archived text: 18c5a895bd2c6211e2a4dc6afb9ef59ac5fb1bea09a7f700a2956aaf585b9ef3
Stable URL of this page: https://metraipolis.com/documento/dc_76facccffda3

How to cite

Robust Function Calling for LLM Agents Under Interface Drift — arXiv:2610.23342 — arXiv (en), https://arxiv.org/abs/2610.23342 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76facccffda3 (Metraipolis archive dc_76facccffda3, sha256 18c5a895bd2c6211e2a4dc6afb9ef59ac5fb1bea09a7f700a2956aaf585b9ef3)

BibTeX

@misc{dc76facccffda3,
  title = {Robust Function Calling for LLM Agents Under Interface Drift — arXiv:2610.23342},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23342},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76facccffda3; sha256 18c5a895bd2c6211e2a4dc6afb9ef59ac5fb1bea09a7f700a2956aaf585b9ef3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23342. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-augmented language-model agents rely on interface text: tool descriptions, argument schemas, and the candidate tool list shown at inference time. These interfaces often change after deployment even when the underlying tool semantics remain fixed, creating a practical reliability problem for function-calling systems. We study this failure mode as interface drift and evaluate whether a lightweight, training-free repair layer can recover robustness without retraining the base model. Our method, SchemaShield-Lite, combines schema validation, candidate-set retry for missing tool names, and one-shot constrained repair. On Qwen3.5-9B, it raises DICE-300 accuracy from 0.717 to 0.813 and BFCL-200 accuracy from 0.580 to 0.805, recovering 19/22 and 33/45 drift-induced failures with no observed repair harms. Naive retry does not explain the gains. Ablations show that candidate-set drift, especially distractor tools, accounts for most observed damage, while description and schema edits alone are less harmful. The results position validation-and-repair as a practical robustness layer for deployed LLM-agent tool use.

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); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.23342 — 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 2026-10-19T08:39:10.078Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).