Cover Image

Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vilas, Martina G., Yousefi, Safoora, Nushi, Besmira, Horvitz, Eric, Balachandran, Vidhisha
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models
by: Moayeri, Mazda, et al.
Published: (2024)

BenchAgents: Multi-Agent Systems for Structured Benchmark Creation
by: Butt, Natasha, et al.
Published: (2024)

Eureka: Evaluating and Understanding Large Foundation Models
by: Balachandran, Vidhisha, et al.
Published: (2024)

Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
by: Balachandran, Vidhisha, et al.
Published: (2025)

LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs
by: Cai, Yanan, et al.
Published: (2025)

Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models
by: Adiga, Rishabh, et al.
Published: (2024)

Diversity of Thought Improves Reasoning Abilities of LLMs
by: Naik, Ranjita, et al.
Published: (2023)

Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
by: Shayegani, Erfan, et al.
Published: (2025)

ZEBRAARENA: A Diagnostic Simulation Environment for Studying Reasoning-Action Coupling in Tool-Augmented LLMs
by: Zhao, Wanjia, et al.
Published: (2026)

Reasoning Up the Instruction Ladder for Controllable Language Models
by: Zheng, Zishuo, et al.
Published: (2025)

Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models
by: Bordt, Sebastian, et al.
Published: (2024)

Phi-4-reasoning Technical Report
by: Abdin, Marah, et al.
Published: (2025)

Accurate Measures of Vaccination and Concerns of Vaccine Holdouts from Web Search Logs
by: Chang, Serina, et al.
Published: (2023)

Detecting Data Contamination in LLMs via In-Context Learning
by: Zawalski, Michał, et al.
Published: (2025)

Trace Length is a Simple Uncertainty Signal in Reasoning Models
by: Devic, Siddartha, et al.
Published: (2025)

MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation
by: Joshi, Siddharth, et al.
Published: (2025)

Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
by: Ding, Wenxuan, et al.
Published: (2023)

SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
by: Huh, Gio, et al.
Published: (2025)

Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis
by: Zou, Junyi
Published: (2026)

FOL-Traces: Verified First-Order Logic Reasoning Traces at Scale
by: Lee, Isabelle, et al.
Published: (2025)

FASTTRACK: Fast and Accurate Fact Tracing for LLMs
by: Chen, Si, et al.
Published: (2024)

MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
by: Li, Shuyue Stella, et al.
Published: (2024)

InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
by: Wei, Chengwei, et al.
Published: (2026)

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
by: Zheng, Ruijie, et al.
Published: (2024)

Metric Temporal Equilibrium Logic over Timed Traces
by: Becker, Arvid, et al.
Published: (2023)

Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation
by: Zhang, Lingzhe, et al.
Published: (2026)

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
by: Yuksekgonul, Mert, et al.
Published: (2023)

The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models
by: Tan, Xue Wen, et al.
Published: (2025)

The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
by: Rezazadeh, Navid, et al.
Published: (2026)

ReasonOps: Operator Segmentation for LLM Reasoning Traces
by: Lee, Daniel, et al.
Published: (2026)

Temporal Smoothness Doubly Robust Learning for Debiased Knowledge Tracing
by: Zhan, Peilin, et al.
Published: (2026)

Revisiting the UID Hypothesis in LLM Reasoning Traces
by: Gwak, Minju, et al.
Published: (2025)

TRAIL: Trace Reasoning and Agentic Issue Localization
by: Deshpande, Darshan, et al.
Published: (2025)

Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
by: Chen, Sixing, et al.
Published: (2026)

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
by: Kambhampati, Subbarao, et al.
Published: (2025)

The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
by: Bachmann, Gregor, et al.
Published: (2026)

Reasoning Traces Shape Outputs but Models Won't Say So
by: Hao, Yijie, et al.
Published: (2026)

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
by: Gourabathina, Abinitha, et al.
Published: (2026)

Tracing Uncertainty in Language Model "Reasoning"
by: Grünefeld, Nils, et al.
Published: (2026)