Metraipolis › archive › dc_0fd01e6e91d2

Recursive Semantic Divergence for LLM Agent Consistency — arXiv:2610.33012

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33012
License (as archived)
CC0-1.0
Archived
2026-10-27T07:59:23.148Z
SHA-256 of the archived text
205cd7fddb552295a3dee125e985643561187c1d5ce8cc128b8f5ef2685e42bd
Stable URL of this page
https://metraipolis.com/documento/dc_0fd01e6e91d2

How to cite

Recursive Semantic Divergence for LLM Agent Consistency — arXiv:2610.33012 — arXiv (en), https://arxiv.org/abs/2610.33012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0fd01e6e91d2 (Metraipolis archive dc_0fd01e6e91d2, sha256 205cd7fddb552295a3dee125e985643561187c1d5ce8cc128b8f5ef2685e42bd)
BibTeX
@misc{dc0fd01e6e91d2,
  title = {Recursive Semantic Divergence for LLM Agent Consistency — arXiv:2610.33012},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33012},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0fd01e6e91d2; sha256 205cd7fddb552295a3dee125e985643561187c1d5ce8cc128b8f5ef2685e42bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Model (LLM) agents with tool use exhibit inconsistent behavior across independent runs from identical states, calling different tools, producing contradictory outputs, or pursuing divergent strategies. This variability compounds over time and undermines deployment reliability. Existing evaluation metrics primarily measure task correctness via completion-based scores and do not capture consistency in agent behavior across executions. Separately, agent behavior is analyzed either at the token level using probability distributions or at the single-response level using semantic clustering, but neither captures how inconsistency propagates across future turns of a trajectory. We introduce Recursive Semantic Divergence (RSD), an unsupervised trajectory-level consistency metric adapted from bisimulation metrics in reinforcement learning. RSD measures the expected cumulative semantic disagreement between two independent rollouts of the same agent from the same state, using natural language inference to detect logical inconsistency. It is defined recursively over future states and approximated by a neural network trained on independent rollouts. The learned metric estimates future divergence from the current state, providing a consistency score at each turn without requiring the full trajectory to complete. When used as a reward signal for fine-tuning, RSD reduces the variation in task progress from 132% to 91% on tau2-bench and from 90% to 44% on toolsandbox, while improving performance across benchmarks and model scales. Training with RSD as an additional reward signal matches supervised fine-tuning performance with substantially lower variance, without requiring ground-truth labels.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.33012 — 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 2026-10-27T07:55:30.783Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).