arXiv AI
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 5
Reasoning Models Don't Just Think Longer, They Move Differently
arXiv:2605. 15454v2 Announce Type: replace-cross Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or following a different internal trajectory.
arXiv AI
Sep 7
Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective
The paper investigates how pause tokens affect fine‑tuning dynamics rather than just inference performance. Experiments on synthetic continual‑learning and math‑reasoning tasks show that masked pause tokens (MBP) reduce overwriting of learned modes and compress downstream‑step information. Across 1B‑8B Qwen and Llama models, MBP consistently improves reasoning scores while preserving language understanding, and the approach also benefits GRPO.
arXiv Computation and Language
Aug 28
TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping
TRACES (Tagging Reasoning Steps for Adaptive Cost‑Efficient Early‑Stopping) is a lightweight framework that tags reasoning steps of large‑language models in real time, enabling adaptive, cost‑efficient early stopping during inference. By monitoring the types of steps generated, the method identifies when models shift their reasoning after arriving at a correct answer, allowing for interpretable stopping criteria. Experiments on mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and knowledge benchmarks (MMLU, GPQA) show token reductions of 20–50% while preserving accuracy, with more conservative thresholds needed for harder tasks such as BeyondAIME and IMO AnswerBench.
arXiv AI
Jun 15
Fractured Chain-of-Thought Reasoning
arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.
arXiv AI
Sep 4
</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
The paper investigates a training‑free early‑exit technique that inserts an end‑of‑think (EoT) token to terminate chain‑of‑thought (CoT) reasoning in large reasoning models. It finds that the injected EoT often fails to cleanly switch the model from reasoning to answering, leading to continued reasoning‑like generation—termed spurious CoT termination—whose length scales with the amount of reasoning saved. By increasing attention to the EoT token through Exit‑token Attention Biasing (EAB), the authors reduce spurious termination and shorten the answering phase across multiple models and benchmarks.
arXiv AI
Sep 16
State of Thought Enables Endogenous Reasoning
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasonin...