AI News

EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems (arxiv.org)

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games (arxiv.org)

Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis (arxiv.org)

LatentPress: Context Compression Beyond Text and Vision (arxiv.org)

Optimizing Byzantine Node Placement in Decentralized Federated Learning (arxiv.org)

MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval (arxiv.org)

Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations (arxiv.org)

Automated Event Log Generation from Unstructured Text Using Finetuned LLMs (arxiv.org)

A Composable Evaluation System for Reproducible Omni-Modal Foundation Model Evaluation (arxiv.org)

Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems (arxiv.org)

CacheBridge: Efficient Cross-Model KV Cache Transfer (arxiv.org)

Denoising Diffusion Generative Models Secretly Calculate Attentions (arxiv.org)

Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning (arxiv.org)

FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study (arxiv.org)

Beyond the Clock: Measuring the Value of Adaptive Revision (arxiv.org)

Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems (arxiv.org)

Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources (arxiv.org)

Towards Generalizable Visually Grounded Exploration of Household Devices (arxiv.org)

Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Survey (arxiv.org)

How Do Language Models Choose Between Context and Memory? (arxiv.org)

Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis (arxiv.org)

Online Self-Weighted Fine-Tuning (arxiv.org)

Patterning in Practice: Debiasing Reward Models with Susceptibilities (arxiv.org)

Dual Process Motion Planning (arxiv.org)

H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning (arxiv.org)

FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue (arxiv.org)

Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate (arxiv.org)

Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs (arxiv.org)

Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents (arxiv.org)

Space Generative AI with Solar Energy Harvesting (arxiv.org)

ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning (arxiv.org)

User Representation via Cross Multi-source Behavior Pre-training for Mobile Games (arxiv.org)

WorldBench: Culturally Grounded Benchmark for Multilingual Agents (arxiv.org)

QILP-0: Constructing Observational Declarative Twins of Quantum Circuits (arxiv.org)

AgentFactory: Towards Automated Agentic System Design and Optimization (arxiv.org)

Data-Driven Persona-Conditioned Agents for A/B Test Simulation (arxiv.org)

Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees (arxiv.org)

Figures as Programs: Recursive Generation of Editable Scientific Figures (arxiv.org)

Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance (arxiv.org)

VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences (arxiv.org)

RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation (arxiv.org)

In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access? (arxiv.org)

CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training (arxiv.org)

CoBRA: Learning Tool-Use Boundaries via Counterfactual Margins (arxiv.org)

A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI (arxiv.org)

Energy-Based Transformers as Predictors of Reading Difficulty (arxiv.org)

Steer, Don't Solve: Training Small Critic Models for Large Code Agents (arxiv.org)

Dense Process Supervision for Search Agents via Fact Utility Estimation (arxiv.org)

MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes (arxiv.org)

Revisiting Face Recognition for Monozygotic Twins: The Celeb Twins Test Set (arxiv.org)