Reasoning papers
What AI researchers are reading: the papers the Hugging Face community picks each day, and new arXiv submissions in the directions we follow. Titles and abstracts are arXiv’s; every paper links to arXiv.
Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning
Souhaila Djaffal, Amna Jamal, Gagana Madhugiri Devaraja et al.
Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially…
Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models
Dong Han, Jin Zhang, Kunyue Yang
Large language models (LLMs) increasingly exhibit capabilities that resemble human Learning by Thinking (LbT), the acquisition of new insight through internal processes such as explanation and reasoning, without new external input. A systematic account of the cognitive mechanisms behind these capabilities, and of…
Auditing the Judge: Internal Signals for LLM Reasoning Assurance
Mayank Gulati, Gerhard Wunder
Language-model systems use self-judgment to decide which answers to release, review, or recompute. Because intervention is costly, an assurance score must rank errors well at the available budget, not merely over the full ranking. We compare the judge's continuous verdict-token score with a supervised correctness…
Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning
Wenqi Zhou, Leonardo Baldo, Kai Goebel et al.
Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this…
Breakdown of Autoregressive Multi-Step Reasoning Under Concentrated vs. Diffuse Attention Head Dropout
Karol Struniawski
During extended wakefulness, mammalian neocortical networks experience localized periods of transient neuronal silence termed off-states. Here, we examine how analogous spatiotemporally concentrated disruptions affect sequential reasoning in autoregressive Large Language Models (LLMs). Evaluating 250 paired…
MMDM: Measuring Massive Multitask Decision Making
Junhao Shen, Qing Zong, Yue Guo et al.
System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on existing benchmarks, where prior…
Mixed Signals: Weight-Space Programming for EEG and ECG
Dara Varam, Taraneh Aminosharieh Najafi, David Atienza
Weight-space programming allows language models to read a trained neural network's weights and edit them. This opens the door to ``training'' by reasoning rather than through gradient descent. Prior work has demonstrated its functionality and promise for game-playing networks and fixing specific failures in…
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
Weida Wang, Benteng Chen, Yigeng Jiang et al.
We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these…
Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics Engines
Chentao Cao, Zhanke Zhou, Sangni Duan et al.
Spatial reasoning requires understanding how objects and observers are arranged in a scene and how their relations change with viewpoint or movement. Vision-language models (VLMs) typically perform both steps through model-internal reasoning, forming an implicit scene interpretation from partial views and imagining…
Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking
Bowen Zuo, Yue Yu, Dongruo Zhou et al.
Diffusion language models (DLMs) generate text through iterative denoising, where decisions about which tokens to commit or remask strongly affect output quality. Existing certainty-aware strategies rely on instantaneous confidence or entropy, but these local signals can be misleading on difficult reasoning…
CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse
Peter Belcak, Greg Heinrich, Saurav Muralidharan et al.
Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We show that once a task has been reasoned through, the application of its solution to a new problem instance can be done very efficiently and…