7
Large Multimodal Model-Based Environment-Aware Mobility Management
This paper explores the integration of large multimodal models to improve mobility management in wireless networks by predicting user trajectories and making real-time decisions.
7
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
This paper frames institutional and regulatory changes in adaptive socio-technical systems as a transfer-learning problem within multi-agent environments.
7
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
This paper proposes using reinforcement learning to correct systematic residual errors in continuous 3D motor imagery decoding for brain-computer interfaces.
7
AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation
The paper proposes AdvNav, a behavior-guided black-box adversarial attack method targeting the vulnerabilities of Vision-and-Language Navigation systems.
7
From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth
This study introduces RouteCast, an evaluation framework designed to assess model-generated strategic routes when ground truth feedback is delayed or private.
7
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
The UNIT framework addresses semantic-structural separation and knowledge imbalance in graph continual learning by leveraging large language models.
7
Exploring Agentic Workflows for Generating High Quality Math Visual Aids
The paper examines how agentic workflows can be used to generate accurate and pedagogically effective mathematical diagrams for middle school education.
7
Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction
The paper presents a framework that utilizes rule-aligned small language models and multi-agent self-correction to generate and validate autonomous industrial control policies.
7
Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking
The paper introduces the Format Sensitivity Index and Parseability Sensitivity Index to measure how minor formatting variations in prompt wrappers affect LLM benchmarking scores.
7
中信建投：计算机板块半年报预告陆续披露，AI算力硬件持续高景气
CSC Financial reports that semi-annual earnings previews confirm high demand for AI servers and intelligent computing infrastructure, while AI software applications are beginning to show revenue recovery.
7
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
A new study explores the need for AI agents to develop task-aware execution capabilities to better estimate the complexity of workflows and avoid inefficient resource usage.
7
FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
FFAvatar uses a Transformer-based 3D Gaussian approach to enable the rapid, incremental construction of animatable 4D head avatars from sparse portrait images.
7
Learning When to Trust in Contextual Social Bandits
A new study identifies a failure mode called contextual sycophancy, where reinforcement learning agents receive biased feedback from evaluators in specific critical scenarios.
7
RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers
The authors present a text-guided audio editing method that utilizes rectified flow matching and diffusion transformers to achieve better semantic alignment.
7
Self-Regulated Reading with AI Support: An Eight-Week Study with Students
A longitudinal study of college students reveals how AI chatbot interactions influence cognitive engagement and reading habits during academic tasks.
7
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
This study presents a method for training branching neural networks to perform multiple algorithmic reasoning tasks simultaneously.
7
Understanding Sources of Demographic Predictability in Brain MRI via Disentangling Anatomy and Contrast
A study investigates how anatomical and contrast factors in brain MRI scans contribute to demographic predictability, highlighting potential biases in medical AI.
7
Research Novelty in Information Systems Journals After ChatGPT: Differences Across Institutional Language Contexts
An analysis of academic publications indicates that the adoption of large language models has influenced the novelty of research output in information systems journals.
7
SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
SheetMind is a new multi-agent system that utilizes large language models to automate spreadsheet tasks through hierarchical instruction decomposition.
7
AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
AgentLens is a new benchmark designed to evaluate coding agents by assessing the quality of their entire interaction trajectory rather than just final task outcomes.
7
When Does Personality Composition Matter for Multi-Agent LLM Teams?
Researchers investigated how personality-based prompting affects the task performance of multi-agent LLM teams, finding that communication styles significantly influence collaborative outcomes.
7
The One-Word Census: Answer-Choice Conformity Across 44 Language Models
An analysis of 44 language models reveals a strong tendency toward convergent behavior when prompted to select single words from open-ended categories.
7
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
TerraZero provides a procedural simulation environment and training stack to support the development of autonomous driving agents through large-scale self-play.
7
From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation
The proposed CARE-PPO framework integrates uncertainty estimation into reinforcement learning fine-tuning to reduce hallucinations and improve confidence in language-based quantitative predictions.