Metraipolis › archive › dc_f5b331fda839

HEXIS: Compiling Agent Skills into Extended Finite State Machines — arXiv:2609.30123

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30123
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:32.072Z
SHA-256 of the archived text
8dba1acd6006d0a7d1171a80eaaeb8dd0900bbfb03dbfee8b2fcfcecca94dc5d
Stable URL of this page
https://metraipolis.com/documento/dc_f5b331fda839

How to cite

HEXIS: Compiling Agent Skills into Extended Finite State Machines — arXiv:2609.30123 — arXiv (en), https://arxiv.org/abs/2609.30123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5b331fda839 (Metraipolis archive dc_f5b331fda839, sha256 8dba1acd6006d0a7d1171a80eaaeb8dd0900bbfb03dbfee8b2fcfcecca94dc5d)
BibTeX
@misc{dcf5b331fda839,
  title = {HEXIS: Compiling Agent Skills into Extended Finite State Machines — arXiv:2609.30123},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30123},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5b331fda839; sha256 8dba1acd6006d0a7d1171a80eaaeb8dd0900bbfb03dbfee8b2fcfcecca94dc5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent skills provide instructions and reusable knowledge, yet agents have to frequently infer which action to take next. This skill's execution paradigm combines task reasoning with control decisions, which could cause the agent to act improperly or omit necessary steps. To improve agent compliance for skills, we introduce HEXIS, which compiles agent skills into extended finite state machines (FSM) that separate knowledge from control flow. Skill knowledge is incorporated into local instructions that guide reasoning and generation within states. The machine records execution progress and intermediate results, while explicit transition conditions determine subsequent operations. Our incremental compiler first maps skill clauses and tool interfaces to state operations, local instructions, data bindings, and transitions. It then aligns development traces with existing states to identify missing operations and dependencies. These are incorporated by adding or reusing states and refining their connections. Updates are accepted only after static checks and replay of the current and all previously accepted traces. Across four benchmarks and four executors, HEXIS improves success over Skill + ReAct by 16.2 percentage points on average. Qwen3.8-27B reduces execution tokens by 38.4-88.9% across benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.30123 — 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 2026-10-08T03:50:57.879Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).