Real-time AI-curated news from 97,914+ articles across 50+ sources. Sentiment analysis, importance scoring, and key takeaways — updated every 15 minutes.
Researchers introduce EDMolGPT, a generative AI model that uses electron density data from protein binding pockets to design novel drug molecules. The approach improves upon existing methods by incorporating physically grounded density information rather than empty pocket structures, enabling more accurate molecular generation with realistic 3D conformations.
Researchers introduced a benchmark testing whether vision-language model (VLM) agents can recognize themselves in mirrors, a cognitive capability that emerges only in some animal species. Results show self-identification through reflection occurs mainly in stronger VLMs, while weaker models fail to extract self-relevant information despite viewing their reflections, revealing that language-based self-reference alone does not guarantee grounded self-understanding.
Researchers propose IMAX, a framework that uses trainable prefix tuning to improve exploration in reinforcement learning with verifiable rewards (RLVR) for language model reasoning. The approach addresses entropy collapse by creating diverse reasoning trajectories, achieving performance gains up to 11.60% in Pass@4 accuracy across multiple model scales.
Researchers introduce FRACTAL, a novel state space model architecture that integrates fractional measure theory to improve long-sequence modeling by balancing short-term sensitivity with long-term memory retention. The approach achieves 87.11% on the Long Range Arena benchmark, outperforming existing SSM models like S5, addressing a fundamental trade-off in temporal sequence analysis.
Researchers introduce M³ (Multi-scale Morton Measure), a framework that improves neural surrogate models for physical simulations by addressing training bias from discretized data sampling. The method achieves up to 4.7× error reduction in volumetric cases and maintains superior performance even with 90% data reduction, demonstrating that data distribution strategy significantly impacts operator learning efficiency.
Researchers introduce Ace-Skill, a co-evolutionary framework that improves multimodal AI agents by optimizing both data sampling and knowledge organization. The system achieves 35% performance gains on tool-use benchmarks and enables smaller models to inherit capabilities from larger ones without additional training.
Researchers introduce OPT-BENCH, a benchmark evaluating whether large language models can self-improve through iterative feedback in complex problem spaces. Testing 19 LLMs across machine learning and NP-hard problems reveals that while stronger models adapt better, even the most advanced systems remain constrained by their base capabilities and fall short of human expert performance.
Researchers propose Safety Internal (SInternal), a framework that trains large reasoning models to verify the safety of their own outputs rather than relying on external compliance mechanisms. The approach demonstrates that models can internalize safety understanding through verification tasks, significantly improving robustness against adversarial jailbreaks and out-of-domain attacks.
Researchers introduce PnP-Corrector, a framework that improves long-term forecasting for coupled dynamical systems by separating error correction from physics simulation. The method achieves 29% error reduction in 300-day ocean-atmosphere forecasts by training a correction agent to counteract systematic biases that accumulate when multiple interacting systems compound prediction errors.
Researchers demonstrate that Fourier Neural Operators (FNOs) used for PDE simulation can be formally verified using SMT solvers by exploiting their piecewise-linear structure once weights are fixed. While exact encoding provides sound proofs and counterexamples on small models, scalability remains limited, revealing a fundamental tradeoff between formal verification rigor and practical applicability for production neural operators.
A new position paper argues that despite functioning as useful co-scientists, agentic AI systems are fundamentally not designed for truly autonomous scientific discovery due to challenges in problem selection bias, insufficient tacit knowledge in training data, compressed output diversity, and lack of real-world experimental feedback loops.
Researchers have optimized Alpamayo 1, a reasoning-based autonomous driving system, by redesigning it from multi-reasoning to single-reasoning architecture while accelerating diffusion-based action generation. The optimization achieves a 69.23% latency reduction while maintaining trajectory diversity and prediction quality, demonstrating that system-level efficiency improvements are critical for practical autonomous driving deployment.
Researchers introduce EAPO, an exploration-aware reinforcement learning framework that enables LLM agents to selectively explore uncertain scenarios before acting. The method uses fine-grained reward functions and adaptive exploration mechanisms to improve decision-making across text and GUI-based agent benchmarks.
Researchers have formalized the sufficient conditions for applying the Heuristic Rating Estimation (HRE) method, a decision-making framework that evaluates alternatives through pairwise comparisons and reference weights. The study examines both arithmetic and geometric computational approaches for complete and incomplete comparison datasets, demonstrating that arithmetic variants provide optimal inconsistency estimates.
Researchers introduce Re²Math, a new benchmark for evaluating large language models' ability to retrieve relevant mathematical theorems and lemmas from academic literature during proof construction. The benchmark reveals significant gaps in current AI systems, with the best model achieving only 7.0% accuracy despite retrieving valid statements, indicating AI struggles to verify applicability to specific proof contexts.
Researchers introduce CATO (Charted Axial Transformer Operator), a neural operator architecture that solves partial differential equations (PDEs) on complex geometries more efficiently than existing methods. By learning geometry-adaptive coordinate transformations and incorporating derivative-aware physics supervision, CATO achieves 26.76% performance improvement over competing approaches while reducing parameters by 82%.
SearchSkill is a new framework that teaches language models to perform more effective web searches by explicitly planning queries through reusable skill cards rather than treating search as an undifferentiated action. The system maintains an evolving skill bank that improves from failure patterns, demonstrating better performance on knowledge-intensive QA tasks with fewer wasted queries and improved reasoning accuracy.
UxSID is a new machine learning framework that models long user behavior sequences using semantic grouping and dual-level attention, achieving state-of-the-art performance with a 0.337% revenue lift in large-scale advertising tests. The approach balances computational efficiency with semantic awareness by using Semantic IDs rather than item-specific search methods.
Researchers introduce Constant-Target Energy Matching (CTEM), a unified framework for density estimation that handles continuous, discrete, and mixed-variable data types within a single objective function. CTEM replaces traditional density-ratio regression with a bounded energy-difference transform, eliminating instability issues and partition-function estimation requirements while delivering improved sample quality across diverse data domains.
Researchers conduct a comprehensive benchmarking study of expert-guided reinforcement learning methods, revealing three critical failure modes that single-paper evaluations miss. They propose a decision rule based on pre-training observables to guide method selection, introducing EDGE as a new design point that exposes exploitable architectural dimensions.
Researchers present MCP-Cosmos, a framework integrating World Models into the Model Context Protocol ecosystem to enhance LLM agent planning and execution. The approach demonstrates measurable improvements in tool success rates and parameter accuracy across multiple benchmark tasks by enabling agents to simulate outcomes before taking actions.
BoostAPR is a new AI framework that improves automated program repair by using dual reward models and reinforcement learning to identify which code edits actually fix bugs. The system achieves significant improvements on multiple benchmarks, including 40.7% on SWE-bench Verified, demonstrating that more granular feedback mechanisms can substantially enhance AI's ability to repair software vulnerabilities.
Open Ontologies is an open-source Rust-based system that combines LLM-driven ontology engineering with formal OWL reasoning and stable matching alignment. The research demonstrates that stable 1-to-1 matching is the critical factor for ontology alignment quality, achieving F1 scores competitive with state-of-the-art systems, while structured tool access via Model Context Protocol significantly outperforms raw file reading for LLM interaction.
Researchers demonstrate that language models develop semantic role understanding (who-did-what-to-whom comprehension) primarily during pre-training, though fine-tuning still improves performance. Using linear probes on frozen transformer models, they find semantic role information emerges from language modeling objectives alone, with representation structure becoming more distributed as models scale.
Researchers present a theoretical framework for inferring the preferences and reward functions of learning agents through observation, extending inverse reinforcement learning beyond its traditional assumption that observed agents act optimally. The work establishes mathematical guarantees for preference learning algorithms when agents are either no-regret learners or converge to optimal Boltzmann policies.
