Image de couverture de livre

Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Chang, Waldemar
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Probing the Trajectories of Reasoning Traces in Large Language Models
par: Ballon, Marthe, et autres
Publié: (2026)

Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories
par: Qu, Zhan, et autres
Publié: (2026)

Tracing Uncertainty in Language Model "Reasoning"
par: Grünefeld, Nils, et autres
Publié: (2026)

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
par: Twist, Lukas, et autres
Publié: (2026)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
par: Wang, Changsheng, et autres
Publié: (2025)

Do Sparse Autoencoders Identify Reasoning Features in Language Models?
par: Ma, George, et autres
Publié: (2026)

PORT: Preference Optimization on Reasoning Traces
par: Lahlou, Salem, et autres
Publié: (2024)

Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces
par: Imperial, Joseph Marvin, et autres
Publié: (2025)

d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation
par: Wang, Guanghan, et autres
Publié: (2025)

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning
par: Zhu, Yekun, et autres
Publié: (2025)

Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
par: Liu, Shuo, et autres
Publié: (2026)

SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
par: Huh, Gio, et autres
Publié: (2025)

Post-Training as Reweighting: A Stochastic View of Reasoning Trajectories in Language Models
par: Bu, Dake, et autres
Publié: (2025)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
par: Yue, Murong, et autres
Publié: (2024)

Adaptive Time Series Reasoning via Segment Selection
par: Messica, Shvat, et autres
Publié: (2026)

Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
par: Kim, Minsu, et autres
Publié: (2025)

A Critical Review of Causal Reasoning Benchmarks for Large Language Models
par: Yang, Linying, et autres
Publié: (2024)

Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
par: Williams, Jonathan, et autres
Publié: (2026)

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
par: Chowdhury, Sanjoy, et autres
Publié: (2026)

CASK: Core-Aware Selective KV Compression for Reasoning Traces
par: Kim, Buseong, et autres
Publié: (2026)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
par: Dai, Xinnan, et autres
Publié: (2025)

Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
par: Zhang, Jianxiong, et autres
Publié: (2026)

ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
par: Cai, Meng, et autres
Publié: (2026)

Clever Materials: When Models Identify Good Materials for the Wrong Reasons
par: Jablonka, Kevin Maik
Publié: (2026)

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
par: Zhang, Zhongwang, et autres
Publié: (2024)

Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
par: Ren, Zirui, et autres
Publié: (2026)

ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
par: Kwon, Yongchan, et autres
Publié: (2025)

Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMs
par: Marin, Javier
Publié: (2024)

Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
par: Damirchi, Hamed, et autres
Publié: (2026)

Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models
par: Pan, Yuchen, et autres
Publié: (2026)

R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
par: Chen, Zhuokun, et autres
Publié: (2025)

Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
par: Wang, Yiming, et autres
Publié: (2024)

ProcessBench: Identifying Process Errors in Mathematical Reasoning
par: Zheng, Chujie, et autres
Publié: (2024)

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
par: Ding, Bowen, et autres
Publié: (2025)

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
par: Huang, Kexin, et autres
Publié: (2026)

Segment-Aligned Policy Optimization for Multi-Modal Reasoning
par: Gao, Lei, et autres
Publié: (2026)

Convex Compositional Reasoning Models
par: Roketlishvili, Meir, et autres
Publié: (2026)

Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries
par: Li, Yanhang, et autres
Publié: (2026)

Identifiable Latent Polynomial Causal Models Through the Lens of Change
par: Liu, Yuhang, et autres
Publié: (2023)

SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction
par: Phillips, Lawrence, et autres
Publié: (2025)