Metraipolis › archive › dc_cbf015e062cc

Small Reasoning Models are Instruction Followers in Function Calling — arXiv:2608.22472

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.22472
License (as archived): CC0-1.0
Archived: 2026-10-18T07:41:26.555Z
SHA-256 of the archived text: f39e38bec909ba499aa81c2aec35f4e889f32cf9d229c39900e7545f69cddea7
Stable URL of this page: https://metraipolis.com/documento/dc_cbf015e062cc

How to cite

Small Reasoning Models are Instruction Followers in Function Calling — arXiv:2608.22472 — arXiv (en), https://arxiv.org/abs/2608.22472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbf015e062cc (Metraipolis archive dc_cbf015e062cc, sha256 f39e38bec909ba499aa81c2aec35f4e889f32cf9d229c39900e7545f69cddea7)

BibTeX

@misc{dccbf015e062cc,
  title = {Small Reasoning Models are Instruction Followers in Function Calling — arXiv:2608.22472},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22472},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbf015e062cc; sha256 f39e38bec909ba499aa81c2aec35f4e889f32cf9d229c39900e7545f69cddea7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calling accuracy through fine-tuning, reinforcement learning (RL), and multi-agent frameworks, particularly for native function-calling LLMs. This work demonstrates that LLMs achieve superior accuracy in function calling in instruction-following contexts (i.e., standard user-assistant interactions) rather than a tool calling context. We introduce Instruction-Followed Function Calling (IFFC), a novel framework that decouples function-calling logic from the primary LLM and delegates it to a dedicated smaller model operating within the instruction-following paradigm. Our method consistently outperforms both native function calling (NFC) and prompt-based function calling (PFC) baselines, with particularly strong gains on reasoning-oriented LLMs. Furthermore, we demonstrate that IFFC maintains robust performance under aggressive quantization, enabling efficient on-device deployment without significant accuracy degradation. This work establishes a new paradigm for reliable, resource-efficient function calling in edge-computing scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.22472 — 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 2026-10-18T07:37:52.721Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).