arXiv AI October 23, 2026 By Tingxin Yang, Zefeng Wang, Mengyue Wang, Jinhe Bi, Xingcheng Zhou, Volker Tresp, Yunpu Ma

DeepLook: Uncertainty-Guided Branching with Lookahead Confidence for Efficient Reasoning

DeepLook is a training‑free decoding framework that uses segment‑level confidence to guide branching during inference. It only expands the search tree at points of high uncertainty and ranks candidate continuations by Average Lookahead Confidence (ALC), a mean confidence over fixed‑horizon rollouts, before finalizing and voting on a pruned subset. Experiments on four mathematics benchmarks show that DeepLook matches or surpasses DeepConf‑low in 12 of 16 settings while reducing token usage by 87.3%, though its advantage disappears on the knowledge‑intensive GPQA‑Diamond task due to hallucinations receiving high ALC.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 28

DeepLook: Deeper Thinking with Lookahead

arXiv:2607. 22602v1 Announce Type: new Abstract: Inference-time scaling has emerged as a powerful paradigm for improving large language model reasoning, often delivering larger gains on difficult reasoning tasks than parameter scaling alone.

By Tingxin Yang, Zefeng Wang, Mengyue Wang, Xingcheng Zhou, Yunpu Ma

llms benchmarks

arXiv AI

Jun 16

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention

arXiv:2510. 13940v4 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency.

By Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

llms efficiency benchmarks

Hugging Face Trending Papers

Sep 29

Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs

As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertaint...

llms benchmarks

arXiv AI

Oct 15

DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning

arXiv:2610.18862v1 Announce Type: cross Abstract: Reasoning models achieve strong performance through long chains of thought (CoT), but often spend more tokens than needed to solve a problem. Existin...

By Minghao Luo, Liang Chen

agents benchmarks

arXiv AI

Sep 30

Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning

arXiv:2609.37066v1 Announce Type: cross Abstract: Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed...

By Hongyang Li, Yiming Zhu, Xiao Li, Caesar Wu, Said Mammar, Pascal Bouvry

llms fine-tuning efficiency

arXiv AI

Oct 1

Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering

arXiv:2609.38962v1 Announce Type: new Abstract: Recent work on hallucination detection in large language models has shown that, for a fixed pre-trained model and reasoning task, it is possible to est...

By Litian Liu, Qiqi Hou, Yubing Jian, Reza Pourreza, Mohammad Ghavamzadeh, Roland Memisevic, Yao Qin, Hong Cai

llms safety

One email a morning, machine-written

Related stories

DeepLook: Deeper Thinking with Lookahead

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention

Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs

DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning

Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning

Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering