The Geometry of Reasoning: Flowing Logics in Representation Space
arXiv:2510.09782v1 Announce Type: new Abstract: We study how large language models (LLMs) “think” through their representation space. We propose a…
Learning Neural Exposure Fields for View Synthesis
arXiv:2510.08279v2 Announce Type: replace-cross Abstract: Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and…
CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts
arXiv:2510.09278v1 Announce Type: cross Abstract: Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions…
CapGeo: A Caption-Assisted Approach to Geometric Reasoning
arXiv:2510.09302v1 Announce Type: cross Abstract: Geometric reasoning remains a core challenge for Multimodal Large Language Models (MLLMs). Even the most…
On the optimization dynamics of RLVR: Gradient gap and step size thresholds
arXiv:2510.08539v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language…
Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents
arXiv:2510.08619v1 Announce Type: new Abstract: Large-scale scientific datasets — spanning health biobanks, cell atlases, Earth reanalyses, and more — create…
Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
arXiv:2510.07024v2 Announce Type: replace-cross Abstract: LLMs are remarkable artifacts that have revolutionized a range of NLP and AI tasks. A…
Counterfactual Identifiability via Dynamic Optimal Transport
arXiv:2510.08294v1 Announce Type: cross Abstract: We address the open question of counterfactual identification for high-dimensional multivariate outcomes from observational data.…
Iterated Agent for Symbolic Regression
arXiv:2510.08317v1 Announce Type: cross Abstract: Symbolic regression (SR), the automated discovery of mathematical expressions from data, is a cornerstone of…
Benchmarking LLM Causal Reasoning with Scientifically Validated Relationships
arXiv:2510.07231v2 Announce Type: replace-cross Abstract: Causal reasoning is fundamental for Large Language Models (LLMs) to understand genuine cause-and-effect relationships beyond…