Research

Paper

AI LLM March 11, 2026

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

Authors

Xinyan Jiang, Ninghao Liu, Di Wang, Lijie Hu

Abstract

Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress (displacement) and Stability (curvature), we reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns (stalled displacement with high curvature fluctuations). Leveraging these signatures, our probabilistic framework achieves competitive performance and superior robustness across diverse benchmarks. Crucially, TRACED bridges geometry and cognition by mapping high curvature to ''Hesitation Loops'' and displacement to ''Certainty Accumulation'', offering a physical lens to decode the internal dynamics of machine thought.

Metadata

arXiv ID: 2603.10384
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-11
Fetched: 2026-03-12 04:21

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.10384v1</id>\n    <title>Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability</title>\n    <updated>2026-03-11T03:58:43Z</updated>\n    <link href='https://arxiv.org/abs/2603.10384v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.10384v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress (displacement) and Stability (curvature), we reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns (stalled displacement with high curvature fluctuations). Leveraging these signatures, our probabilistic framework achieves competitive performance and superior robustness across diverse benchmarks. Crucially, TRACED bridges geometry and cognition by mapping high curvature to ''Hesitation Loops'' and displacement to ''Certainty Accumulation'', offering a physical lens to decode the internal dynamics of machine thought.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-11T03:58:43Z</published>\n    <arxiv:comment>Under review</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Xinyan Jiang</name>\n    </author>\n    <author>\n      <name>Ninghao Liu</name>\n    </author>\n    <author>\n      <name>Di Wang</name>\n    </author>\n    <author>\n      <name>Lijie Hu</name>\n    </author>\n  </entry>"
}