Metraipolis › archive › dc_7443abd26ab7
ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression — arXiv:2609.32852
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32852
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:52:25.411Z
- SHA-256 of the archived text
6d0ee09bf94ec88548d7fc6ae1fcf14ec205c36281e298598a7c98f2ad456818- Stable URL of this page
https://metraipolis.com/documento/dc_7443abd26ab7
How to cite
ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression — arXiv:2609.32852 — arXiv (en), https://arxiv.org/abs/2609.32852 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7443abd26ab7 (Metraipolis archive dc_7443abd26ab7, sha256 6d0ee09bf94ec88548d7fc6ae1fcf14ec205c36281e298598a7c98f2ad456818)
BibTeX
@misc{dc7443abd26ab7,
title = {ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression — arXiv:2609.32852},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32852},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7443abd26ab7; sha256 6d0ee09bf94ec88548d7fc6ae1fcf14ec205c36281e298598a7c98f2ad456818},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32852. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Large Language Model (LLM)-based agents demonstrate strong capabilities in long-horizon tasks by interleaving reasoning with external environment interactions, the continuous accumulation of context rapidly creates a critical memory bottleneck. Existing memory compression methods rely on task-specific optimization or external auxiliary models, introducing significant computational overhead. Furthermore, the resulting compressed representations tend to lose structured relationships, leading to information dilution, attention collapse, and degraded decision consistency. To address these limitations, we propose Auto-Regressive State Machine (ARSM), a lightweight training-free framework that enables in-situ reasoning compression through structured state evolution. ARSM introduces two key components: (i) a trajectory abstraction mechanism that reorganizes interaction histories into compact Hypothesis-Action-Result (HAR) micro-chains; (ii) a dynamic state machine that regulates hierarchical memory through atomic operations and a compression-control parameter. These components are unified within an auto-regressive, self-compressive generation space, where each model output jointly performs external action execution and internal state updates. We evaluate ARSM on Webshop, Multi-Objective Multi-Hop QA, and SWE-Bench Lite datasets. Experimental results show that ARSM maintains the task performance while simultaneously reducing token consumption, offering a practical, cost-effective route toward scalable autonomous agents for long-horizon tasks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.32852 — 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 2026-10-07T21:27:08.470Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).