AI Research News Feeds for December 26th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization
• Quantum-Inspired Multi Agent Reinforcement Learning for Exploration Exploitation Optimization in UAV-Assisted 6G Network Deployment
• Proceedings of the 20th International Conference on Knowledge, Information and Creativity Support Systems (KICSS 2025)
• MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
• Erkang-Diagnosis-1.1 Technical Report
• Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
• AIAuditTrack: A Framework for AI Security system
• Mixture of Attention Schemes (MoAS): Learning to Route Between MHA, GQA, and MQA
• Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence
• AI-Driven Decision-Making System for Hiring Process
• From Fake Focus to Real Precision: Confusion-Driven Adversarial Attention Learning in Transformers
• Quantifying Laziness, Decoding Suboptimality, and Context Degradation in Large Language Models
• Eidoku: A Neuro-Symbolic Verification Gate for LLM Reasoning via Structural Constraint Satisfaction
• Bridging the AI Trustworthiness Gap between Functions and Norms
• From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Education
• From artificial to organic: Rethinking the roots of intelligence for digital health
• A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
• Safety Alignment of LMs via Non-cooperative Games
• MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs
• The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents
• A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines
• FinAgent: An Agentic AI Framework Integrating Personal Finance and Nutrition Planning
• TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control
• Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation
• A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care
• Inspection Planning Primitives with Implicit Models
• Cooperation Through Indirect Reciprocity in Child-Robot Interactions
• Efficient Asynchronous Federated Evaluation with Strategy Similarity Awareness for Intent-Based Networking in Industrial Internet of Things
• Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication
• X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis
• NotSoTiny: A Large, Living Benchmark for RTL Code Generation
• Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction
• One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
• Mesh-Attention: A New Communication-Efficient Distributed Attention with Improved Data Locality
• Policy-Conditioned Policies for Multi-Agent Task Solving
• PhononBench:A Large-Scale Phonon-Based Benchmark for Dynamical Stability in Crystal Generation
• Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking
• Learning Factors in AI-Augmented Education: A Comparative Study of Middle and High School Students
• Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Consulting, Data Analyst, and Management Tasks
• Improving Autoformalization Using Direct Dependency Retrieval