The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can b…

The paper proposes a category-theoretic framework for agentic AI that models scientific discovery not as answer generation, but as a verifiable transition and revision of the underlying representation…

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

This paper presents EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery.

The paper introduces Influence-Guided Symbolic Regression (IGSR), a novel framework that uses granular influence scores to guide LLMs in efficiently searching for and discovering complex mathematical…

This review surveys advanced techniques—including generative models, multimodal learning, and closed-loop workflows—for automated inverse materials design, enabling the targeted discovery of novel cry…

AutoScientists introduces a decentralized, self-organizing team of AI agents that significantly improves long-running scientific experimentation by enabling parallel exploration and knowledge sharing.

This paper introduces ATLAS, an active learning framework for discovering interpretable behavioral models in cognitive science.

The paper introduces 'Matter to Mechanism,' a novel benchmark designed to rigorously evaluate AI co-scientists' ability to generate plausible, mechanism-grounded solution hypotheses for complex materi…

The paper introduces Compass, an expert-guided LLM agent framework that successfully extracts and integrates thousands of previously inaccessible marine lead records from vast corpora of scientific pa…

The paper introduces AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-t…

This paper systematically evaluates the consistency of popular causal discovery benchmarks against real-world scientific literature, revealing significant variability in their accuracy.

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

The paper demonstrates that achieving Post-Quantum Cryptography (PQC) readiness requires treating cryptographic discovery as a governance capability to manage complex dependencies and prioritize risk…

MolLingo is a multi-agent system that significantly improves automated molecular design by integrating domain-specific chemical reasoning and structural context into LLMs, outperforming state-of-the-a…

The paper introduces KnowledgeGain, a novel metric that measures the actual knowledge gained by readers from science news, and demonstrates its use in optimizing news generation to improve reader lear…

AutoForest is an end-to-end system that automatically generates publication-ready forest plots directly from biomedical papers, streamlining the labor-intensive process of meta-analysis.