Metraipolis › archive › dc_29080e63bc15

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents — arXiv:2608.16002

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16002
License (as archived)
CC0-1.0
Archived
2026-10-18T18:06:52.462Z
SHA-256 of the archived text
4de0a948f3e5790d0c0cd1fab2f494b582af68b3c0606ef5498ebf4380a54b5e
Stable URL of this page
https://metraipolis.com/documento/dc_29080e63bc15

How to cite

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents — arXiv:2608.16002 — arXiv (en), https://arxiv.org/abs/2608.16002 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29080e63bc15 (Metraipolis archive dc_29080e63bc15, sha256 4de0a948f3e5790d0c0cd1fab2f494b582af68b3c0606ef5498ebf4380a54b5e)
BibTeX
@misc{dc29080e63bc15,
  title = {From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents — arXiv:2608.16002},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16002},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29080e63bc15; sha256 4de0a948f3e5790d0c0cd1fab2f494b582af68b3c0606ef5498ebf4380a54b5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16002. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods largely rely on local signals, such as token probabilities, predictive entropy, or per-step confidence, and therefore overlook the long-range dependencies through which errors accumulate across an execution trajectory. As a result, they may fail to identify agent failures whose causes originate several reasoning or interaction steps before the final answer. We propose RUPA (Relational Uncertainty Propagation for Agents), a trajectory-level UQ framework for LLM agents. RUPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges. It then propagates uncertainty over this graph to capture how execution risk accumulates and transfers across interaction steps. The propagated signal is combined with trajectory-level behavioral features and goal-alignment information to produce a confidence estimate for the full agent trajectory. We evaluate RUPA on representative agent benchmarks, including $\tau$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families. Experimental results show that RUPA consistently outperforms existing UQ methods by providing more accurate uncertainty estimates, enabling earlier failure detection, and improving uncertainty-guided agent execution across diverse agent tasks. These results demonstrate that explicitly modeling relational dependency is crucial to reliable UQ for long-horizon LLM agents, providing a practical foundation for trustworthy agent execution.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16002 — 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 2026-10-18T16:29:14.067Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).