Article

PhasePilot: Auditing and steering phase boundaries in budgeted in-context reasoning

2026-02-20

Abstract excerpt

<title>Abstract</title> <p>Reasoning performance in in-context learning can change discontinuously as inference-time resources vary, even at fixed model size. We characterize this behavior with an operational framework that treats the prompt as a budgeted state space defined by context cap k, demonstration count N, and task depth D. We define an order parameter m (exact-match accuracy) and a sensitivity χ=∂m/∂log...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 29e79674-dfdb-5e34-a435-637e346d31ae
DOI: 10.21203/rs.3.rs-8912612/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

PhasePilot: Auditing and steering phase boundaries in budgeted in-context reasoningDOI 10.21203/rs.3.rs-8912612/v1Read

Reasoning in Large Language Models: From Chain-of-Thought to Massively Decomposed Agentic ProcessesSemantic proximity Read

Reasoning Distillation by Prompt OptimizationSemantic proximity Read

Multi-Agent based Dynamic Anchors for Interpretation of Deep Learning ClassifiersSemantic proximity Read

Flow-by-Flow: Content-Judgment Bypass for Governing AI Output in High-Loss DomainsSemantic proximity Read

Protocol-Dependent Resolution in Finite-Sample Model SelectionSemantic proximity Read

Move Quality Beyond Arena: Pure Distillation for Small Go NetworksSemantic proximity Read

WITHDRAWN: The Physics of Thought: Reasoning as Thermodynamic Relaxation in Generative ModelsSemantic proximity Read

Flow-by-Flow: Content-Judgment Bypass for Governing AI Output in High-Loss DomainsSemantic proximity Read

Automatic Discovery of Intra-Class Sub-Structure for Supervised Tabular Classification: Offline Clustering vs. Joint Sub-Center TrainingSemantic proximity Read

The Reality of Prompt Engineering: Simplicity Often Outperforms Sophistication in Reasoning TasksSemantic proximity Read

Stress-Testing the Reasoning Competence of LLMs with Proofs Under Minimal FormalismSemantic proximity Read

GeneBench-Pro: Evaluating Multistage Statistical Reasoning in Genomics, Quantitative Biology, and Translational BiomedicineSemantic proximity Read