Metraipolis › archive › dc_02d7acdfbeef
StateGate: A Behavioral-Fidelity Prompt Optimization Method for Long-Chain LLM Agents — arXiv:2611.01585
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01585
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:33:04.428Z
- SHA-256 of the archived text
0862b3f9720e61457a2086e8571199407271c1c449e5fc5ae1372aa8a61f36fa- Stable URL of this page
https://metraipolis.com/documento/dc_02d7acdfbeef
How to cite
StateGate: A Behavioral-Fidelity Prompt Optimization Method for Long-Chain LLM Agents — arXiv:2611.01585 — arXiv (en), https://arxiv.org/abs/2611.01585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02d7acdfbeef (Metraipolis archive dc_02d7acdfbeef, sha256 0862b3f9720e61457a2086e8571199407271c1c449e5fc5ae1372aa8a61f36fa)
BibTeX
@misc{dc02d7acdfbeef,
title = {StateGate: A Behavioral-Fidelity Prompt Optimization Method for Long-Chain LLM Agents — arXiv:2611.01585},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01585},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02d7acdfbeef; sha256 0862b3f9720e61457a2086e8571199407271c1c449e5fc5ae1372aa8a61f36fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Currently, long-chain LLM agents commonly suffer from behavioral degradation in complex tasks, where prompts are written in full but steps are not executed in full. To address this issue, existing approaches face three major challenges. First, constraints are strongly bound to their textual carriers; once natural-language constraint sentences are removed, their binding force vanishes. Second, the execution process lacks independent verification, as the evidence for judgment is often supplied by the executing party itself, leading to the failure of self-referential validation. Third, existing remediation schemes are difficult to generalize, and hard-coded mechanisms cannot be transferred across tasks. In this paper, we propose StateGate, a novel prompt-optimization scheme that transforms semantic constraints into symbolic gates enforced by an external deterministic runtime. By decoupling the content of a constraint from its carrier of efficacy, StateGate achieves behavioral fidelity in long-chain tasks without losing the binding force of the prompt. Specifically, we first propose four independent compression strategies (deduplication, generalization, externalization, and text-to-gating) together with their corresponding decision chains, enabling principled prompt symbolization. Second, we design a three-component architecture consisting of a state file, a validator, and an orchestrator, which thoroughly separates judgment authority from execution authority. Third, we formally prove that the compliance of symbolic constraints is independent of context size. Finally, we validate the framework on a vulnerability-discovery task in the security domain; the results show that StateGate achieves 100% execution closure and accurate vulnerability detection. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2611.01585 — 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 2026-11-03T18:12:23.790Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).