📌 Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models

Saurabh Mathur et al.

#arXiv #cs.AI

OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression

Sixu Chen et al.

#arXiv #cs.AI #cs.MA

Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models

Hongyu Shi et al.

#arXiv #cs.AI

Harness Evolution Hits a Ceiling: When Weight Training Should Begin

Yuan Tian et al.

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

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies

Yi Wen et al.

#arXiv #cs.AI

Workerville: Towards an Organizational Behavior Account of Agent Safety

Hanjun Luo et al.

#arXiv #cs.AI

The Operator Mismatch Problem: Deploying BEV Perception with Portable GPU Compute

Rohit Verma, Anand V Bodas

#arXiv #cs.AI

From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers

Gerard Grau Garc\'ia et al.

#arXiv #cs.AI

EvoSim: Learning to Model, Modeling to Learn

Yun-Wei Song et al.

#arXiv #cs.AI #cs.CE

ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems

Weilin Jin et al.

#arXiv #cs.AI

Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild

Yuxuan Cao et al.

#arXiv #cs.AI

DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration

Yingda Shen et al.

#arXiv #cs.AI #cs.SD

Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback

Zexuan Liu, Yuning Yang, Tiancheng Zhao

#arXiv #cs.AI #cs.LG #math.OC

Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs

Andrea Wynn (Nathan) et al.

#arXiv #cs.AI #cs.MA

Whose Ground Truth? Embracing Ambiguity in Human-Centered AI

Jingyao Wu et al.

#arXiv #cs.AI #cs.LG

Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction

Yipeng Li et al.

#arXiv #cs.AI

📌 Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Kaiser Sun et al.

#arXiv #cs.AI #cs.CL

LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs

Nihal Jain et al.

#arXiv #cs.AI

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Haoyu Zhao et al.

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

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents

Guanghao Wu, Zhuo Cai, Shoujin Wang

#arXiv #cs.AI