Agent Trust Infrastructure (ATI): A Federated Identity, Trust, Attestation, and Accountability Architecture for Cross-Organization Autonomous AI Agents

California State Polytechnic University, Pomona
Abstract

WoRD: Diffusion-Based Posterior Inference for Online Goal Recognition

CLAIR Lab; Technion – Israel Institute of Technology
Abstract

RSI-Prime: Training Models to Train Models

Sun Yat-sen University; Mind Lab; Chongqing University; Harbin Institute of Technology, Shenzhen
Abstract

Hidden-State Similarity Predicts Re-Elicitation After Inoculation Prompting

Université Laval; Mila – Québec AI Institute; Université de Montréal
Abstract

Colombo: A Frontier-to-Frontier Autoresearch System for Oracle-Based Optimization

Peking University
Abstract

The Resolution Hypothesis: Agent Evolution’s Key Is Identifying Improvements

ShanghaiTech University; ByteDance; BIGAI; SUSTech
Abstract

Values Shape What Self-Improving Coding Agents Build

Cognizant AI Lab
Abstract

Deep Reinforcement Learning for Heat Pump and Underfloor Heating Control: An End-to-End Case Study

Universidad de Granada; Georg Fischer Building Flow Solutions
Abstract

FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond

Tsinghua University; Harbin Engineering University; BNRist; THUIBCS
Abstract

ForecastGym: A Live, Controlled, and Replayable Benchmark for Forecasting Agents

Carnegie Mellon University; Jilin University
Abstract

PeriaTrace: Tooth-Level Grounding Diagnosis and Patient-Facing Explanations from Periapical Radiographs

Nankai University; Key Laboratory of Data and Intelligent System Security, Ministry of Education; Tianjin Union Medical Center; The First Affiliated Hospital of Nankai University; The Second Hospital of Tianjin Medical University
Abstract

PhysScope: Agentic Multimodal Physics Reasoning with Grounded Visual Memory

Abstract

Residual-Guided Lightweight Reinforcement Learning for Risk-Aware Trajectory Selection with a Frozen World Model

RWTH Aachen University; Monash University
Abstract

RagHarnessDebugger: Jev-Guided Agentic RAG in Contract Inference Repair Auditing

Harvard University; Illinois Tech - Chicago Kent College of Law; Bucerius Law School; Singapore Management University; Stanford University; Bommarito Consulting, LLC; Massachusetts Institute of Technology
Abstract

Structured AI ideation yields physical strategies for epithelial barrier repair

Asteromorph; Gachon University; Gachon Advanced Institute for Health Science & Technology; Seoul National University; Lee Gil Ya Cancer and Diabetes Institute
Abstract

VITAL: A Framework for Validating Agentic AI in Pharmaceutical Drug Development and Clinical Trial Operations

AstraZeneca Boston; AstraZeneca Barcelona; AstraZeneca Cambridge; NVIDIA; IQVIA Frankfurt; IQVIA London; IQVIA Durham; University of California, Irvine
Abstract

Done, But Still Working: Anytime Evaluation of When Coding Agents Should Stop

Huawei Technologies Ltd.
Abstract

Born for the Task: Rethinking Quantum Chemistry with Foresighted Agentic Computing

Peking University; Moore Threads; University of Chinese Academy of Sciences; Michigan Technological University; Tsinghua University
Abstract

Outcome-Balanced PPO and Policy-Induced Flow Rectification for Flow-Based VLA Policies

Tsinghua University; The Hong Kong University of Science and Technology
Abstract

Against Coercion: AI Alignment as a Synthetic Social Contract

Ruhr University Bochum; University of Cologne
Abstract

Why ChatPaper

  • Interest-Driven Paper Curation

    Describe your interests as you like, be it keywords or sentence, you’ll get relevant papers every day via AI semantic matching.

  • Top Conferences, One-Stop

    IJCAI, ICML, CVPR, KDD... Access papers from top AI conferences, all in one tool, for free.

  • Paper Management Made Easy

    Keep your research organized with our bookmarking feature. Build a well-structured knowledge hub at your fingertips.

  • Chat With Any Paper

    Got questions? Ask in ChatDOC with one single click. Use AI to pull data, clarify terms, and verify facts with our precise word-level tracing feature.

See how it works

Watch now 1 min