GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning

Jingyao Zhang, Yun Li, Lu Han

#arXiv #cs.AI #cs.CL #cs.CV #cs.LG

From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents

Juanyang Xu et al.

#arXiv #cs.AI

Think Before You Paint: Recursive Latent Reasoning for Diffusion Models

Pawe{\l} Skier\'s et al.

#arXiv #cs.AI #cs.LG

How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression

Xijie Gong et al.

#arXiv #cs.AI #cs.LG

SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models

Miao Yu et al.

#arXiv #cs.AI

Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study

Lin Wu et al.

#arXiv #cs.AI #cs.CY

DrugTargetWorld: A Synthetic Biobank for Training and Benchmarking AI Scientists

Samuel Margolis et al.

#arXiv #cs.AI

Ream: Unfolding Mutual Awareness in Human-Agent Workspaces

Peiling Jiang et al.

#arXiv #cs.AI #cs.HC

MIMESIS: Learning User Simulators as Training Environments for Interactive Agents

Hoang Phan et al.

#arXiv #cs.AI

RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment

Tianruo Rose Xu et al.

#arXiv #cs.AI #cs.LG

Trajectory Abstraction for the Science of Language Agent Behavior

Tianqiang Yan

#arXiv #cs.AI #cs.CL

Few Bits, One Law: Toward W2A4KV2

Kai Yi et al.

#arXiv #cs.AI #cs.CL #cs.LG

Finding Blind Spots in AppWorld and WorkArena Task Verifiers

Richard Abrich

#arXiv #cs.AI #cs.SE

Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network

Brandon Ho, Nikola Rogers, Seung-Kyum Choi

#arXiv #cs.AI #cs.LG #cs.MA #cs.RO

SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions

Yizhen Xie, Mengyang Liu

#arXiv #cs.AI #cs.LG #q-fin.PM #q-fin.TR

Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation

Haonan Deng, Park Sinchaisri

#arXiv #cs.AI

Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions

Akira Kitaoka

#arXiv #cs.AI #math.OC #math.ST #stat.ML #stat.TH

A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers

Evgenia Ilia, Wilker Aziz

#arXiv #cs.AI

LLM-Enabled UAV Dispatch: A System-Level Survey and Taxonomy

Xiao Han et al.

#arXiv #cs.AI #cs.SY #eess.SY

We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents

Kefan Liu et al.

#arXiv #cs.AI