AI News

LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling (arxiv.org)

Beyond Channel Data: Configuration-Enriched Radio Foundation Models (arxiv.org)

TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent (arxiv.org)

From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning (arxiv.org)

Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement (arxiv.org)

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis (arxiv.org)

DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks (arxiv.org)

IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints (arxiv.org)

Lifelong Context Adaptation through Bidirectional Memory-Skill Learning (arxiv.org)

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution (arxiv.org)

MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports (arxiv.org)

RSIHub: A Composable Framework for Agent-Evolution Methods (arxiv.org)

Understanding Communication Failures in Multi-Agent LLM Systems (arxiv.org)

Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation (arxiv.org)

Tampered ML: Evaluating LLM Judgment of Machine Learning Research (arxiv.org)

REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories (arxiv.org)

ReMedI: Inference-Time Refinement and Self-Distillation for Controllable Molecular Optimization (arxiv.org)

TTT in VLA Models: Exploring Training with Human Demonstrations (arxiv.org)

AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents (arxiv.org)

Guided Zero-Shot Anomaly Explanation for Anonymized Crowd Video Monitoring: Context, Categorization, and Spatial Localization (arxiv.org)

Controlled Evaluation of EEG Foundation Models: Random Initialisation, Band-Power and Validation-Selected Probes (arxiv.org)

Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders (arxiv.org)

HyScale: Scaling Long-Context Training for Learned Sparse Attention (arxiv.org)

ACVA-Bench: Beyond Prompt Following in Abstract Concept Visualization Ability for Text-to-Image Models (arxiv.org)

MI-MIDI 2: From Observation to Control with Sparse Autoencoders in Text-to-MIDI Generation (arxiv.org)

OpenHome: From Perception to Insight in Smart-Home Camera Videos (arxiv.org)

Spectra: Multi-Scale Implicit Decomposition for Deepfake Detection (arxiv.org)

Agentic AI Defense: Decode-Time Provenance Binding for MCP (arxiv.org)

A Mathematical Theory of the Jacobian Lens (arxiv.org)

RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy (arxiv.org)

Kolibri: A Sovereign European Model on the Pareto Frontier (arxiv.org)

Learning Structured Sparsity for Large Models: Bridging Model Compressibility and Efficient Inference (arxiv.org)

Knowing When to Stop: The Evidence-Action Gap in Coding Agents (arxiv.org)

Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima (arxiv.org)

When Agents Fail: Model or Harness--Who's to Blame? (arxiv.org)

Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations (arxiv.org)

CASE: Confusion-Aware Skill Evolution for Frozen Multimodal Emotion Models (arxiv.org)

CauProphet: Teaching Agents to Develop Causal Cognition like Humans (arxiv.org)

Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings (arxiv.org)

ALLMTS: Automated LLM-based Medical Triage System (arxiv.org)

POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories (arxiv.org)

When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning (arxiv.org)

Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents (arxiv.org)

LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents (arxiv.org)

DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage (arxiv.org)

Adaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents (arxiv.org)

FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification (arxiv.org)

Do AI-for-Science Agents Preserve Model Safety? (arxiv.org)

PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots (arxiv.org)

RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training (arxiv.org)