AI Papers

Revisiting LLM Reasoning via Information Bottleneck. arxiv.org/abs/2507.18391

Reasoning Beyond the Obvious: Evaluating Divergent and Convergent Thinking in LLMs for Financial Scenarios. arxiv.org/abs/2507.18368

The AlphaPhysics Term Rewriting System for Marking Algebraic Expressions in Physics Exams. arxiv.org/abs/2507.18337

Foundations for Risk Assessment of AI in Protecting Fundamental Rights. arxiv.org/abs/2507.18290

Comparing Non-minimal Semantics for Disjunction in Answer Set Programming. arxiv.org/abs/2507.18198

Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory. arxiv.org/abs/2507.18178

Logical Characterizations of GNNs with Mean Aggregation. arxiv.org/abs/2507.18145

Actively evaluating and learning the distinctions that matter: Vaccine safety signal detection from emergency triage notes. arxiv.org/abs/2507.18123

AlphaGo Moment for Model Architecture Discovery. arxiv.org/abs/2507.18074

Does visualization help AI understand data?. arxiv.org/abs/2507.18022

E.A.R.T.H.: Structuring Creative Evolution through Model Error in Generative AI. arxiv.org/abs/2507.18004

Synthesis of timeline-based planning strategies avoiding determinization. arxiv.org/abs/2507.17988

SMARTAPS: Tool-augmented LLMs for Operations Management. arxiv.org/abs/2507.17927

I2I-STRADA -- Information to Insights via Structured Reasoning Agent for Data Analysis. arxiv.org/abs/2507.17874

ASP-Assisted Symbolic Regression: Uncovering Hidden Physics in Fluid Mechanics. arxiv.org/abs/2507.17777

TAI Scan Tool: A RAG-Based Tool With Minimalistic Input for Trustworthy AI Self-Assessment. arxiv.org/abs/2507.17514

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning. arxiv.org/abs/2507.17512

Automated Hybrid Grounding Using Structural and Data-Driven Heuristics. arxiv.org/abs/2507.17493

LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning. arxiv.org/abs/2507.17482

An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models. arxiv.org/abs/2507.17477