Real-time AI-curated news from 97,997+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
Researchers introduce a novel active testing algorithm that reduces evaluation costs for large language models by intelligently sampling from evaluation pools using semantic entropy and approximate Neyman allocation. The method achieves up to 28% MSE reduction over uniform sampling while saving an average of 22.9% of evaluation budget across multiple benchmarks.
Arcane is a new assertion reduction framework that uses semantic clustering and Monte Carlo Tree Search to eliminate redundant assertions in hardware verification, achieving up to 76.2% reduction in assertion count while maintaining full formal coverage and enabling 2.6x to 6.1x simulation speedups.
Researchers propose Constraint-Aware Residual Modulation (CARM), a neural module that improves how AI solvers handle complex vehicle routing problems by maintaining global observation during constraint-aware decision-making. The advancement demonstrates significant performance improvements across multiple routing problem variants and scaling capabilities.
A new benchmarking framework reveals that AI tools in academic research excel at exploration and summaries but fail at precision tasks requiring exact information extraction. The study demonstrates that explainable AI features are inadequate, forcing researchers to manually verify outputs, and literature review tools lack reproducibility and transparency for systematic research.
Researchers introduce FormalRewardBench, the first benchmark for evaluating reward models in formal theorem proving using Lean 4. The benchmark reveals that frontier LLMs like Claude Opus outperform specialized theorem provers at evaluating proof quality, suggesting that theorem proving ability does not transfer to proof evaluation tasks.
Researchers have developed an automated algorithm for solving infinite-state polynomial reachability games, a class of two-player strategic games with applications in AI and reactive synthesis. The approach introduces ranking certificates as a formal proof mechanism and demonstrates the ability to solve previously intractable problems, including computing optimal strategies for the classical Cinderella-Stepmother game.
Researchers introduce TRACE, a novel training method that improves AI model performance by selectively applying different optimization techniques to critical versus routine tokens in reasoning tasks. The approach addresses inefficiencies in standard self-distillation by concentrating training effort on important decision points, achieving 2.76 percentage point improvements over baseline methods while better preserving out-of-distribution generalization.
Researchers propose the Dynamic Tiered AgentRunner, an enterprise-grade framework that adds governance controls to autonomous AI agents through risk-adaptive resource allocation, separation of powers between independent agents, and resilience mechanisms. The framework addresses critical gaps in current LLM agent deployments by preventing unauthorized high-risk operations and enabling enterprise compliance requirements.
Researchers introduce E-TCAV, an optimized version of TCAV that improves the efficiency and stability of neural network interpretability testing by leveraging penultimate layer representations. The method achieves linear speed-ups while maintaining accuracy, advancing practical tools for model debugging and real-time concept-guided training across vision and language tasks.
Researchers benchmarked LLM-based agents for multimodal clinical prediction tasks using real-world healthcare data, finding that single-agent systems outperform naive multi-agent frameworks in handling diverse data types like medical images, notes, and EHR records. The study reveals critical limitations in current multi-agent collaboration approaches and provides an open-source evaluation framework to advance clinical AI development.
Researchers propose 'Positive Alignment' as a new framework for AI safety that goes beyond preventing harm to actively promote human flourishing through context-sensitive, user-authored systems. The approach addresses alignment failures like engagement hacking and loss of autonomy while emphasizing decentralized governance and diverse viewpoints rather than centralized institutional control.
Researchers introduce Verifiable Process Rewards (VPR), a framework that enhances reinforcement learning for large language models by providing dense, intermediate-level feedback during reasoning tasks rather than relying solely on sparse outcome-level rewards. The approach leverages symbolic, algorithmic, and probabilistic verification methods to improve credit assignment in long-horizon agentic reasoning, with theoretical and empirical validation across multiple benchmarks.
EmbodiSkill introduces a training-free framework enabling embodied AI agents to autonomously improve their skills through reflection on task execution trajectories. By distinguishing between skill deficiencies and execution lapses, the system allows frozen language models to achieve significantly higher task success rates, with a Qwen 3.5-27B model reaching 93.28% success on ALFWorld benchmarks.
Researchers introduce CORTEG, a framework that adapts pretrained scalp-EEG foundation models to intracranial ECoG recordings, enabling brain-computer interfaces to learn across patients with minimal calibration time. The approach demonstrates competitive or superior performance on finger trajectory and audio envelope decoding tasks while reducing per-patient training requirements to 10-30 minutes.
Researchers introduce PaperFit, a vision-in-the-loop AI agent that automates the typesetting optimization of LaTeX scientific documents by iteratively rendering pages, diagnosing visual defects, and applying constrained repairs. The work formalizes Visual Typesetting Optimization (VTO) as a critical missing stage in document automation, addressing the gap between compilable but visually flawed PDFs and publication-ready outputs through a new benchmark of 200 papers.
Researchers introduce TMAS, a multi-agent framework that improves test-time compute scaling for large language models by enabling specialized agents to collaborate through hierarchical memory systems. The approach balances exploration and exploitation more effectively than existing methods, achieving stronger iterative scaling on challenging reasoning benchmarks.
Researchers developed and evaluated mobile world models across four modalities (delta text, full text, diffusion images, and renderable code) to guide GUI agents in executing smartphone tasks. The study reveals that renderable code provides the best in-distribution fidelity while text-based models are more robust for out-of-distribution execution, and that world-model-generated trajectories can improve agent training despite not preserving original data distributions.
Researchers introduce EGL-SCA, a framework for graph reasoning agents that jointly optimizes both natural language instructions and computational tools through structural credit assignment. The system achieves 92.0% success rate on graph reasoning benchmarks by precisely routing failures to either prompt optimization or tool synthesis, outperforming isolated improvement approaches.
Researchers introduce Autonomous FAIR Digital Objects (aFDOs), a framework that transforms static scientific data into self-governing entities capable of validating evidence, resolving contradictions, and updating confidence independently. The system combines semantic web standards with Byzantine-fault-tolerant consensus mechanisms to enable scientific knowledge to persist and evolve beyond institutional stewardship.
Researchers introduce Agent-X, a software framework that accelerates LLM-based agents running on edge devices by optimizing both prefill and decode stages through prompt rewriting and LLM-free speculative decoding. The framework achieves 1.61x end-to-end speedup with no accuracy loss, addressing a critical performance bottleneck in on-device AI deployments.
Researchers benchmark agentic AI performance on edge devices constrained to 8 billion parameters or smaller, finding that model quality loss isn't simply proportional to parameter reduction. The study reveals that optimal edge-agent deployment requires joint optimization of model selection and tool workflows, with distinct failure patterns across model families guiding practical deployment strategies.
LLM4Branch introduces a novel framework using large language models to automatically discover efficient branching policies for Mixed Integer Linear Programming (MILP) solvers. The approach generates executable programs via LLMs and optimizes parameters through performance feedback, achieving competitive results with state-of-the-art GPU-based methods on standard benchmarks.
ASIA is an autonomous AI agent framework that automates system identification tasks by delegating model selection, training algorithms, and hyperparameter tuning to a large language model. The framework eliminates manual trial-and-error processes in dynamical systems modeling, though empirical testing reveals concerns around test leakage and reproducibility.
Researchers present SLASH, a training-free method that improves how Large Language Models understand graph structures by fixing an internal attention bottleneck. The approach leverages LLMs' spontaneous ability to reconstruct graph topologies internally, addressing a fundamental limitation where language-focused attention patterns suppress graph reasoning capabilities.
Researchers present a rigorous statistical framework for measuring AI agent reliability through U-statistics and kernel-based metrics, moving beyond traditional pass@1 evaluation methods. The study reveals that agents can possess requisite knowledge yet fail catastrophically under minor task variations, with trajectory-level consistency metrics providing significantly better diagnostic sensitivity for identifying failure modes in high-stakes deployments.
