Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems

Diego Gosmar et al.

#arXiv #cs.AI #cs.MA

Condition-Contrastive Extrapolation for On-Policy Distillation of Language Models

Wenxuan Luo et al.

#arXiv #cs.AI

MemScope: Evolving Agent Memory Architectures through Localized Code Repair

Miao Su et al.

#arXiv #cs.AI

Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows

Shirley Anugrah Hayati et al.

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

MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data

Robert Moseley et al.

#arXiv #cs.AI #cs.CV

Temporal Specification Guidance for Text-to-Video Generation

Avishree Khare et al.

#arXiv #cs.AI #cs.CV

When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following

Shaoang Li, Yanhang Shi, Jian Li

#arXiv #cs.AI #cs.CL

ARIA: Runtime Inspection and Amendment for Multi-Agent Systems

Bolin Shen, Yushun Dong

#arXiv #cs.AI #cs.CL

AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks

Zhanke Zhou et al.

#arXiv #cs.AI #cs.LG

Evaluating Model Capabilities After Benchmark Saturation

Morio Hamada et al.

#arXiv #cs.AI #cs.LG

Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages?

Trizal Garg et al.

#arXiv #cs.AI #cs.CL

RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST Parsing

Mohammadreza Sediqin, Shlomo Engelson Argamon

#arXiv #cs.AI

Are You Sure Your LLM Is Sure? Repairing and Auditing Confidence

Arijit Dey et al.

#arXiv #cs.AI

DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction

Aozhong Zhang et al.

#arXiv #cs.AI

When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models

Wei Cai et al.

#arXiv #cs.AI

FAOPs: Normal Forms and an Algebra for AI Agent Workflows

Ali Mohammadi Shanghooshabad (JPMorgan Chase, Co.)

#arXiv #cs.AI #cs.DB #cs.PL

RoleQ: Role-Aligned Scales for Converting Language Models to Ternary

Johannes Knittel, Alec Helbling, Hanspeter Pfister

#arXiv #cs.AI #cs.CL

CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering

Yinghua Xu et al.

#arXiv #cs.AI #cs.LG

Quantum Versus Classical Machine Learning for Neuropsychiatric Disorders: A Feature-Matched Multi-Cohort Evaluation

Utsav Poudel et al.

#arXiv #cs.AI

Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

Zhizhuo Kou et al.

#arXiv #cs.AI #cs.CL