AI Research News Feeds for December 26th, 2025

AI RESEARCH PAPERS & ACADEMIC SOURCES

• Improving Autoformalization Using Direct Dependency Retrieval : Abstract: The convergence of deep learning and formal mathematics has spurred research in formal verification. Statement autoformalization, a crucial first step in this process, aims to translate info...
• Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Consulting, Data Analyst, and Management Tasks : Abstract: This paper derives `Scaling Laws for Economic Impacts' -- empirical relationships between the training compute of Large Language Models (LLMs) and professional productivity. In a preregister...
• Learning Factors in AI-Augmented Education: A Comparative Study of Middle and High School Students : Abstract: The increasing integration of AI tools in education has led prior research to explore their impact on learning processes. Nevertheless, most existing studies focus on higher education and co...
• Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking : Abstract: Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applica...
• PhononBench:A Large-Scale Phonon-Based Benchmark for Dynamical Stability in Crystal Generation : Abstract: In this work, we introduce PhononBench, the first large-scale benchmark for dynamical stability in AI-generated crystals. Leveraging the recently developed MatterSim interatomic potential, w...
• Policy-Conditioned Policies for Multi-Agent Task Solving : Abstract: In multi-agent tasks, the central challenge lies in the dynamic adaptation of strategies. However, directly conditioning on opponents' strategies is intractable in the prevalent deep reinfor...
• Mesh-Attention: A New Communication-Efficient Distributed Attention with Improved Data Locality : Abstract: Distributed attention is a fundamental problem for scaling context window for Large Language Models (LLMs). The state-of-the-art method, Ring-Attention, suffers from scalability limitations ...
• One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents : Abstract: Locating the files and functions requiring modification in large open-source software (OSS) repositories is challenging due to their scale and structural complexity. Existing large language ...
• Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction : Abstract: Due to their inherent flexibility and autonomous operation, unmanned aerial vehicles (UAVs) have been widely used in Internet of Medical Things (IoMT) to provide real-time biomedical edge co...
• NotSoTiny: A Large, Living Benchmark for RTL Code Generation : Abstract: LLMs have shown early promise in generating RTL code, yet evaluating their capabilities in realistic setups remains a challenge. So far, RTL benchmarks have been limited in scale, skewed tow...
• X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis : Abstract: The growing complexity of power system operations has created an urgent need for intelligent, automated tools to support reliable and efficient grid management. Conventional analysis tools o...
• Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication : Abstract: Multi-agent decision-making under uncertainty is fundamental for effective and safe autonomous operation. In many real-world scenarios, each agent maintains its own belief over the environme...
• Efficient Asynchronous Federated Evaluation with Strategy Similarity Awareness for Intent-Based Networking in Industrial Internet of Things : Abstract: Intent-Based Networking (IBN) offers a promising paradigm for intelligent and automated network control in Industrial Internet of Things (IIoT) environments by translating high-level user in...
• Cooperation Through Indirect Reciprocity in Child-Robot Interactions : Abstract: Social interactions increasingly involve artificial agents, such as conversational or collaborative bots. Understanding trust and prosociality in these settings is fundamental to improve hum...
• Inspection Planning Primitives with Implicit Models : Abstract: The aging and increasing complexity of infrastructures make efficient inspection planning more critical in ensuring safety. Thanks to sampling-based motion planning, many inspection planners...
• A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care : Abstract: Large language models (LLMs) often match or exceed clinician-level performance on medical benchmarks, yet very few are evaluated on real clinical data or examined beyond headline metrics. We...
• Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation : Abstract: Explainable artificial intelligence (XAI) enables data-driven understanding of factor associations with response variables, yet communicating XAI outputs to laypersons remains challenging, h...
• TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control : Abstract: Traffic simulation is important for transportation optimization and policy making. While existing simulators such as SUMO and MATSim offer fully-featured platforms and utilities, users witho...
• FinAgent: An Agentic AI Framework Integrating Personal Finance and Nutrition Planning : Abstract: The issue of limited household budgets and nutritional demands continues to be a challenge especially in the middle-income environment where food prices fluctuate. This paper introduces a pr...
• A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines : Abstract: The application of agentic AI systems in autonomous decision-making is growing in the areas of healthcare, smart cities, digital forensics, and supply chain management. Even though these sys...
• The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents : Abstract: Autonomous agents powered by LLMs and Retrieval-Augmented Generation (RAG) are proficient consumers of digital content but remain unidirectional, a limitation we term epistemic asymmetry. Th...
• MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs : Abstract: LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections o...
• Safety Alignment of LMs via Non-cooperative Games : Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: gene...
• A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents : Abstract: As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has become a paramount concern. Current safety benchmarks...
• From artificial to organic: Rethinking the roots of intelligence for digital health : Abstract: The term artificial implies an inherent dichotomy from the natural or organic. However, AI, as we know it, is a product of organic ingenuity: designed, implemented, and iteratively improved ...
• From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Education : Abstract: Generative AI enables personalized computer science education at scale, yet questions remain about whether such personalization supports or undermines learning. This scoping review synthesiz...
• Bridging the AI Trustworthiness Gap between Functions and Norms : Abstract: Trustworthy Artificial Intelligence (TAI) is gaining traction due to regulations and functional benefits. While Functional TAI (FTAI) focuses on how to implement trustworthy systems, Normati...
• Eidoku: A Neuro-Symbolic Verification Gate for LLM Reasoning via Structural Constraint Satisfaction : Abstract: Large Language Models (LLMs) frequently produce hallucinated statements that are assigned high likelihood by the model itself, exposing a fundamental limitation of probability-based verifica...
• Quantifying Laziness, Decoding Suboptimality, and Context Degradation in Large Language Models : Abstract: Large Language Models (LLMs) often exhibit behavioral artifacts such as laziness (premature truncation of responses or partial compliance with multi-part requests), decoding suboptimality (f...
• From Fake Focus to Real Precision: Confusion-Driven Adversarial Attention Learning in Transformers : Abstract: Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit subopt...
• AI-Driven Decision-Making System for Hiring Process : Abstract: Early-stage candidate validation is a major bottleneck in hiring, because recruiters must reconcile heterogeneous inputs (resumes, screening answers, code assignments, and limited public evi...
• Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence : Abstract: Large language models (LLMs) face inherent limitations in memory, including restricted context windows, long-term knowledge forgetting, redundant information accumulation, and hallucination ...
• Mixture of Attention Schemes (MoAS): Learning to Route Between MHA, GQA, and MQA : Abstract: The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality bu...
• AIAuditTrack: A Framework for AI Security system : Abstract: The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and risk trac...
• Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning : Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of large language models (LLMs). While prior work focuses on improving model performance through intern...
• Erkang-Diagnosis-1.1 Technical Report : Abstract: This report provides a detailed introduction to Erkang-Diagnosis-1.1 model, our AI healthcare consulting assistant developed using Alibaba Qwen-3 model. The Erkang model integrates approxima...
• MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data : Abstract: Foundation model reliability assessment typically requires thousands of evaluation examples, making it computationally expensive and time-consuming for real-world deployment. We introduce mi...
• Proceedings of the 20th International Conference on Knowledge, Information and Creativity Support Systems (KICSS 2025) : Abstract: This volume presents the proceedings of the 20th International Conference on Knowledge, Information and Creativity Support Systems (KICSS 2025), held in Nagaoka, Japan, on December 3-5, 2025...
• Quantum-Inspired Multi Agent Reinforcement Learning for Exploration Exploitation Optimization in UAV-Assisted 6G Network Deployment : Abstract: This study introduces a quantum inspired framework for optimizing the exploration exploitation tradeoff in multiagent reinforcement learning, applied to UAVassisted 6G network deployment. We...
• BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization : Abstract: Smart home lighting systems consume 15-20% of residential energy but lack adaptive intelligence to optimize for user comfort and energy efficiency simultaneously. We present BitRL-Light, a n...