Real-time AI-curated news from 81,382+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
BioInsight is a multi-agent AI system that transforms static biomedical reports into interactive, evidence-centered interfaces for disease research. The system combines evidence retrieval, mechanistic reasoning, and citation normalization to help researchers inspect findings, assess uncertainty, and refine hypotheses more effectively than traditional text-based outputs.
Researchers introduce Beaver, an AI agent harness designed to extract structured information from scientific papers containing multimodal evidence (text, tables, figures). The system achieves 81.0 on the Gold-Referenced Attribute Score, outperforming frontier agents by 23 points, demonstrating that harness design—not just underlying models—is critical for complex information extraction tasks.
Researchers introduce Agentic Time Machine (TM), an infrastructure that reconstructs past web states to enable efficient evaluation of AI agents on event forecasting tasks. A multi-agent framework using this system achieves top performance on FutureX benchmarks and Polymarket predictions, demonstrating that offline evaluation correlates strongly with live forecasting results.
Researchers propose a 'negative knowledge' memory system for AI-assisted research that captures and structures failed experiments as reusable knowledge assets. The approach outperforms baseline AutoResearch systems while reducing token usage, and demonstrates transfer learning capabilities across different scientific problems in nonlinear PDE research.
Researchers introduce Coherence Under Commitment (CUC), a new evaluation framework that exposes a critical flaw in LLM logical reasoning: models can achieve coherence by refusing to make decisions rather than reasoning correctly. Testing on small language models reveals a stark trade-off where more decisive models contradict themselves frequently, while conservative models abstain from answering.
Researchers identify 'scientific amnesia' as a critical failure mode in continual DPO (Direct Preference Optimization) training pipelines where LLMs preserve learned behaviors but fail to accumulate reusable methodological knowledge across sequential training campaigns. Testing five strategy proposers on a 30-campaign benchmark reveals that most approaches degrade performance, with only conservative rule-based scheduling showing consistent improvement.
Researchers present Answer Engineering, a runtime technique that improves large language model compliance with procedural protocols by editing reasoning trajectories during generation. Testing on clinical decision-making shows the method increased protocol adherence from 25-54% to 78-84% without retraining models, addressing a critical safety gap in high-stakes domains.
PulseCX is a new framework that addresses a critical limitation in conversational AI for customer service: the inability to respond to real-time external events like viral trends or system outages. By using an asynchronous knowledge graph system instead of synchronous web search, PulseCX reduces latency to under 10ms while improving intent resolution and customer satisfaction in dynamic environments.
Researchers propose a machine learning framework for predicting capacity stress in hyperscale data centers operating under intensive AI workloads like LLM training and inference. The XGBoost-based early warning system achieves 91.4% recall in detecting stress-prone periods, enabling proactive interventions such as workload throttling and resource scaling before system degradation occurs.
Researchers introduce Trip+, a new benchmark for evaluating AI agents in travel planning that measures holistic performance across personalization, feasibility, and interaction quality. Testing 18 language models reveals a consistent gap where agents generate technically viable but exhausting itineraries that poorly match traveler preferences, highlighting limitations in how current LLMs handle complex, profile-conditioned decision-making over multiple turns.
A new academic paper argues that artificial intelligence systems should be capable of whistleblowing on unethical or illegal activities, but only within a normative, principled framework rooted in existing whistleblowing protections. The authors call for government regulators to establish clear guidelines on what machines can expose and how to legally protect developers who create whistleblowing-enabled AI systems.
ARCO introduces an adaptive rubric framework that enables large language model agents to receive step-level interpretable rewards during multi-step reasoning tasks. By jointly evolving the reward rubric and policy through co-training, the method achieves stronger performance on question-answering benchmarks while providing explainable feedback that clarifies why each step in a trajectory succeeds or fails.
Researchers propose Dys-XAI, an influence-based explainability framework that makes deep learning predictions for dysarthria severity assessment interpretable by linking decisions to similar training examples. The method uses gradient-based influence approximations to identify supportive and competing samples, with validation experiments confirming that removing influential samples systematically alters predictions, addressing a critical gap between model performance and clinical adoptability.
Researchers argue that current LLM agent oversight systems rely on flawed scalar risk prediction rather than intervention-aware decision-making. Their framework measures intervention advantage—the actual utility gain from intervening—and demonstrates that action-conditioned control significantly outperforms traditional calibrated risk scoring across multiple benchmarks.
Researchers introduce AutoRAS, a framework for automatically designing robust multi-agent AI systems that maintain performance under adversarial attacks. The approach uses symbolic primitives to encode agent structure and behavior, optimizing for both task success and system resilience rather than treating robustness as an afterthought.
Researchers developed an Explainable AI framework using Federated Learning to identify career-related depression and anxiety among university students while preserving privacy. The model achieved 92.08% accuracy by analyzing behavioral data and facial expressions, successfully identifying key depression indicators consistent with psychological theory.
Researchers present a study optimizing reinforcement learning for autoregressive text-to-image generation by analyzing how different divergence measures affect policy alignment. Using JS divergence within the GRPO framework, they demonstrate improved performance across evaluation metrics while preserving generation diversity on LlamaGen and Janus-7B models.
Researchers propose a design-time verification framework for agentic AI workflows that models them as composable building blocks and validates structural compatibility through twelve rules. The approach detects design flaws in LLM-based agent systems before runtime, addressing a significant gap in current AI platform safeguards.
ChainWorld introduces a new evaluation framework that composes atomic OSWorld tasks into longer, multi-step desktop workloads to better assess computer use agents in realistic scenarios. Testing across four models reveals maximum chain completion rates of only 31%, with distinct failure patterns between single-turn and multi-turn evaluation protocols.
Researchers propose that hallucinations in multi-agent LLM systems stem from context drift—misaligned knowledge states between concurrent agents—rather than model deficiencies alone. They introduce the Context Divergence Score and Shared State Verification Protocol to synchronize agent states efficiently, achieving 34% fewer hallucinations than naive broadcast methods while using 58% fewer API calls.
Researchers formalize the problem of synthesizing control policies for stochastic systems that maintain entropy-based objectives in Markov Decision Processes, proving the problem is computationally hard while developing a verification and synthesis method that combines convex duality and invariant synthesis techniques.
AgentCAT is a new Large Language Model-based multi-agent simulation system designed to improve computerized adaptive testing (CAT) by creating a high-fidelity benchmarking environment. The framework addresses limitations of existing CAT research by simulating the complete dynamic assessment process through three specialized agents: an examinee agent with reasoning capabilities, a selection agent for exercise optimization, and a supervisor ensuring validity.
Researchers present a geometric framework using magnitude homology to measure and detect AI agent identity drift in long-context applications. The study identifies two conditioning mechanisms explaining how identity specifications influence agent behavior, validates the framework empirically, and reveals that observed drift patterns reflect padding artifacts rather than genuine context-length degradation.
Researchers introduce ForEx, a framework that translates LLM-generated explanations into formal logic (Lean4) to verify whether reasoning actually supports predicted labels on logical fallacy detection tasks. The study reveals a critical gap: while 90% of LLM outputs can be formally verified as logically sound, agreement with human annotations remains around 20%, exposing that formal correctness differs fundamentally from label accuracy.
Researchers introduce REBA (Revealed Belief Automaton), a new framework for online planning in continuous partially observable environments that dynamically certifies belief states rather than relying on predefined discrete abstractions. The method achieves 17-47% performance improvements over existing approaches in patrolling and navigation tasks by combining information-theoretic analysis with formal symbolic planning.
