Private Retrieval Augmented Generation via Random Projection

Dixi Yao, Tahseen Rabbani, Tian Li

#arXiv #cs.AI #cs.CR

LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents

Qingni Wang et al.

#arXiv #cs.AI

AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning

Bingxiang He et al.

#arXiv #cs.AI #cs.CL

Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?

Jingyu Tang et al.

#arXiv #cs.AI

Data World: Scaling Data Environments from Scratch

Zhanli Li et al.

#arXiv #cs.AI

ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image Processing

Hao Zhang (First Institute of Oceanography et al.

#arXiv #cs.AI

Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents

Yutong Leng et al.

#arXiv #cs.AI #cs.CL

Watts If? A Benchmark for Counterfactual Reasoning About the AI Data Center Buildout

Pankaj Chouhan et al.

#arXiv #cs.AI

FedSkillGit: Federated Skill Evolution via Version Control

Boxun Lan et al.

#arXiv #cs.AI

Sci$\Pi$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents

Youran Sun et al.

#arXiv #cs.AI

Recursive Reward Improvement via Adversarial Meta-Prompt Evolution

Wei Dai et al.

#arXiv #cs.AI #cs.MA

A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering

Yun-Shiuan Chuang et al.

#arXiv #cs.AI #cs.CL

When Reality Outpaces Cognition: A New Scaling Principle for Reliable Intelligence

Ahsan Adeel, Talha Bin Riaz

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

Designing Transformers for Continuous Diffusion Language Models

Weijian Luo et al.

#arXiv #cs.AI

Shortcut Sensitivity in Agent-Safety Evaluations

Hasan Demirkiran, Jens Ernstberger

#arXiv #cs.AI #cs.CR #cs.LG

HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration

Yanchen Deng et al.

#arXiv #cs.AI #cs.CL

Prism-1: Position- and Rival-Independent Scoring for System One Models

Yao Long Teng et al.

#arXiv #cs.AI

📌 Progress Reward Model for Reinforcement Learning via Large Language Models

Xiuhui Zhang et al.

#arXiv #cs.AI

CARA: Causally Guided Retrieval Agent for Question Answering

Weicheng Liu et al.

#arXiv #cs.AI #cs.IR

DeciCAD: Harness-Grounded Learning of Action Policies for CAD Agents

Yufeng Peng et al.

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