No AI summary available for this article.
Why It Matters
LLM agents need to sustain goal-consistent reasoning across long multi-turn interactions under strict resource constraints.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
LLM agents need to sustain goal-consistent reasoning across long multi-turn interactions under strict resource constraints. However, as the multi-turn context accumulates, it can destabilize the underlying LLM's internal representation of task-relevant information from earlier turns, blurring the boundary between constructive reasoning and representation drift. We formulate multi-turn reasoning as a hidden-state trajectory of the underlying LLM that is characterized via two complementary signals: temporal curvature that captures the directional consistency of turn-to-turn updates, and variance...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.30650v1 · Indexed about 2 hours ago