Hugging Face Trending Papers July 29, 2026

Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models

Read the original on Hugging Face Trending Papers →

Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence more effectively or seek information that could improve future decisions. We distinguish these responses by measuring action preference, thinking length, and reported confidence under matched uncertainty.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 30

Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models

arXiv:2607. 26845v1 Announce Type: new Abstract: Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence more effectively or seek information that could improve future decisions.

By Hua-Dong Xiong, Xinyuan Yan, Ji-An Li, Jingming Xue, Marcelo G. Mattar, Robert C. Wilson

llms reinforcement-learning

arXiv AI

Aug 7

Small Foundation Models of Human Cognition and Behaviour

arXiv:2608. 05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions.

By Nick Oh, Fernand Gobet

llms fine-tuning

arXiv AI

1d ago

Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors

arXiv:2608. 16707v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration.

By David Eric Austin, Kaheer Suleman, Jackie Chi Kit Cheung

llms agents reinforcement-learning safety

arXiv AI

Aug 11

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

arXiv:2605. 24396v2 Announce Type: replace Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute.

By Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu, J. Zico Kolter, Andrej Risteski, Aditi Raghunathan

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 16

Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision

arXiv:2606. 15877v1 Announce Type: cross Abstract: Chain-of-thought (CoT) improves large language models' performance in math and symbolic reasoning.

By Alex Bogdan

llms benchmarks

arXiv AI

Aug 5

In-Context Pure Exploration in Continuous Decision Spaces

arXiv:2602. 17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to identify an unknown ground-truth hypothesis with as few queries as possible.

By Alessio Russo, Yin-Ching Lee, Ryan Welch, Aldo Pacchiano

reinforcement-learning

Related stories

Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models

Small Foundation Models of Human Cognition and Behaviour

Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

Free Energy Heuristics: Fast-And-Frugal Cognition as Active Inference Under Uncertain Precision

In-Context Pure Exploration in Continuous Decision Spaces