Large Language Models (LLMs) enhanced with retrieval -- commonly referred to as Retrieval-Augmented Generation (RAG) -- have demonstrated strong performance in knowledge-intensive tasks. However, RAG pipelines often fail when retrieved evidence is incomplete, leaving gaps in the reasoning process. In such cases, \emph{abductive inference} -- the process of generating plausible missing premises to explain observations -- offers a principled approach to bridge these gaps. In this paper, we propose a framework that integrates abductive inference into retrieval-augmented LLMs. Our method detects insufficient evidence, generates candidate missing premises, and validates them through consistency and plausibility checks. Experimental results on abductive reasoning and multi-hop QA benchmarks show that our approach improves both answer accuracy and reasoning faithfulness. This work highlights abductive inference as a promising direction for enhancing the robustness and explainability of RAG systems.

Hypothesis ranking is vital for automated scientific discovery, especially in cost-intensive, throughput-limited natural science domains. Current methods focus on pre-experiment ranking, relying solely on language model reasoning without empirical feedback. We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests. Due to the impracticality of real experiments, we propose a simulator grounded in domain-specific concepts that models hypothesis performance as a function of similarity to a hidden ground truth, perturbed by noise. Validated against 124 hypotheses with experimentally reported outcomes, the simulator approximates real results with consistent trend alignment. Although deviations exist, they mimic wet-lab noise, promoting more robust ranking strategies. We frame experiment-guided ranking as a sequential decision-making problem and propose an in-context reinforcement learning (ICRL) framework. Our LLM-based policy decomposes hypotheses into functional elements, clusters them by mechanistic roles, and prioritizes recombinations based on feedback. Experiments show our approach significantly outperforms pre-experiment baselines and strong ablations. Our toolkit, comprising the simulator and ICRL framework, enables systematic research on experiment-guided ranking, with the policy serving as a strong proof of concept.

Novelty detection in large scientific datasets faces two key challenges: the noisy and high-dimensional nature of experimental data, and the necessity of making statistically robust statements about any observed outliers. While there is a wealth of literature on anomaly detection via dimensionality reduction, most methods do not produce outputs compatible with quantifiable claims of scientific discovery. In this work we directly address these challenges, presenting the first step towards a unified pipeline for novelty detection adapted for the rigorous statistical demands of science. We introduce AutoSciDACT (Automated Scientific Discovery with Anomalous Contrastive Testing), a general-purpose pipeline for detecting novelty in scientific data. AutoSciDACT begins by creating expressive low-dimensional data representations using a contrastive pre-training, leveraging the abundance of high-quality simulated data in many scientific domains alongside expertise that can guide principled data augmentation strategies. These compact embeddings then enable an extremely sensitive machine learning-based two-sample test using the New Physics Learning Machine (NPLM) framework, which identifies and statistically quantifies deviations in observed data relative to a reference distribution (null hypothesis). We perform experiments across a range of astronomical, physical, biological, image, and synthetic datasets, demonstrating strong sensitivity to small injections of anomalous data across all domains.

Scientists have identified more than fifty ways that houses can ignite. It's possible to defend against all of them--but it's arduous, and homeowners can't do it alone. In June, 2012, hundreds of homes in Mountain Shadows, Colorado, a subdivision in the foothills of the Rockies, were reduced to ash during the wind-whipped Waldo Canyon Fire. On a cul-de-sac called Hot Springs Court, however, four dwellings somehow remained standing. The mystery of their survival nagged at Alex Maranghides, a fire-protection engineer at the National Institute of Standards and Technology (), who worked with several colleagues on a meticulous reconstruction of the fire. How did the homes make it through? Was there something special about them--a fireproof roof, say, or a fancy sprinkler system? The team collected weather reports, topographic data, G.P.S. records from fire engines, photos, videos, and property-damage reports.

Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within the broader AI for Science paradigm, where AI systems progress from partial assistance to full scientific agency. Enabled by large language models (LLMs), multimodal systems, and integrated research platforms, agentic AI shows capabilities in hypothesis generation, experimental design, execution, analysis, and iterative refinement -- behaviors once regarded as uniquely human. This survey provides a domain-oriented review of autonomous scientific discovery across life sciences, chemistry, materials science, and physics. We unify three previously fragmented perspectives -- process-oriented, autonomy-oriented, and mechanism-oriented -- through a comprehensive framework that connects foundational capabilities, core processes, and domain-specific realizations. Building on this framework, we (i) trace the evolution of AI for Science, (ii) identify five core capabilities underpinning scientific agency, (iii) model discovery as a dynamic four-stage workflow, (iv) review applications across the above domains, and (v) synthesize key challenges and future opportunities. This work establishes a domain-oriented synthesis of autonomous scientific discovery and positions Agentic Science as a structured paradigm for advancing AI-driven research.

Foundation models (FMs), such as GPT-4 and AlphaFold, are reshaping the landscape of scientific research. Beyond accelerating tasks such as hypothesis generation, experimental design, and result interpretation, they prompt a more fundamental question: Are FMs merely enhancing existing scientific methodologies, or are they redefining the way science is conducted? In this paper, we argue that FMs are catalyzing a transition toward a new scientific paradigm. We introduce a three-stage framework to describe this evolution: (1) Meta-Scientific Integration, where FMs enhance workflows within traditional paradigms; (2) Hybrid Human-AI Co-Creation, where FMs become active collaborators in problem formulation, reasoning, and discovery; and (3) Autonomous Scientific Discovery, where FMs operate as independent agents capable of generating new scientific knowledge with minimal human intervention. Through this lens, we review current applications and emerging capabilities of FMs across existing scientific paradigms. We further identify risks and future directions for FM-enabled scientific discovery. This position paper aims to support the scientific community in understanding the transformative role of FMs and to foster reflection on the future of scientific discovery. Our project is available at https://github.com/usail-hkust/Awesome-Foundation-Models-for-Scientific-Discovery.

The watershed moment Trump changed course on Israel after Netanyahu shattered their once-unbreakable bond: 'We felt betrayed' Kim Kardashian stuns onlookers in horrifying MASKED look at one of Hollywood's biggest galas DAPHNE BARAK: How I delivered the final, fatal blow to Andrew's fast-sinking reputation... and why Palace is right to still be deeply concerned Doctors expose the truth about melatonin... as terrifying side effects soar Gavin Newsom melts down as Pentagon plans to fire artillery shells over California highway during'No Kings' protest Olivia Nuzzi's memoir will reveal juicy text messages with RFK Jr. KENNEDY: Here's the truth of weird drug-fueled orgies in Congress that Tucker Carlson is investigating... it makes me sick to my stomach JANA HOCKING: I've uncovered the ultimate new sex secret and had the best night of my life... no wonder more women are trying it Limp Bizkit bassist Sam Rivers dead at 48 as iconic band pays tribute to'once-in-a-lifetime' talent Insiders reveal dark web of power behind earthquake of'No Kings' protests exploding across America Five safe haven investments if the global economy goes into meltdown (and one under the radar fund to buy RIGHT NOW): As more and more experts warn of a devastating fall in share prices... Inside the King's cold phone call that saw Prince Andrew lose his dukedom and have to cancel Sarah Ferguson's 66th birthday party as Epstein scandal exploded '90s icon looks unrecognizable as she teases her most infamous TV scene in bucket hat during rare outing Antonio Banderas and Melanie Griffith's daughter Stella, 29, weds her childhood sweetheart in dreamy Spanish wedding as actor toasts the newlyweds Stephen A. Smith makes racially-charged double standard accusation against LeBron James amid feud The Duchess of Scandal... who is now plain old Sarah: Fergie's humiliating downfall as King makes moves to'protect' her daughters Green Bay Packers' game in jeopardy with team stranded at airport less than 24 hours before kickoff Selena Gomez makes FIRST red carpet appearance with husband Benny Blanco since wedding as their'perfect' honeymoon is revealed READ MORE: Is there a God? It's a question that has been asked since the beginning of time: does God really exist? Traditionally, science has been the counterargument for the existence of a divine creator. However, French mathematicians Olivier Bonnassies and Michel-Yves Bollore now say that science'has become God's ally'. In a new book, the duo have distilled insights from 62 Nobel Prize winners and more than 100 leading scientists to pinpoint the scientific discoveries that could prove God is real.

Abstract--Chemistry, a long-standing discipline, has historically relied on manual and often time-consuming processes. While some automation exists, the field is now on the cusp of a significant evolution driven by the integration of robotics and artificial intelligence (AI), giving rise to the concept of the robochemist: a new paradigm where autonomous systems assist in designing, executing, and analyzing experiments. Robo-chemists integrate mobile manipulators, advanced perception, teleoperation, and data-driven protocols to execute experiments with greater adaptability, reproducibility, and safety. Rather than a fully automated replacement for human chemists, we envisioned the robochemist as a complementary partner that works collaboratively to enhance discovery, enabling a more efficient exploration of chemical space and accelerating innovation in pharmaceuticals, materials science, and sustainable manufacturing. This article traces the technologies, applications, and challenges that define this transformation, highlighting both the opportunities and the responsibilities that accompany the emergence of the robochemist. Ultimately, the future of chemistry is argued to lie in a symbiotic partnership where human intuition and expertise is amplified by robotic precision and AI-driven insight. The field of chemistry, a cornerstone of modern science and industry, has long been characterized by a blend of theoretical insight and practical, hands-on experimentation.

The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research Intelligence Assistant), a spec-driven, human-in-the-loop framework for automated and interpretable data analysis. ARIA integrates six interoperable layers, namely Command, Context, Code, Data, Orchestration, and AI Module, within a document-centric workflow that unifies human reasoning and machine execution. Through natural-language specifications, researchers define analytical goals while ARIA autonomously generates executable code, validates computations, and produces transparent documentation. Beyond achieving high predictive accuracy, ARIA can rapidly identify optimal feature sets and select suitable models, minimizing redundant tuning and repetitive experimentation. In the Boston Housing case, ARIA discovered 25 key features and determined XGBoost as the best performing model (R square = 0.93) with minimal overfitting. Evaluations across heterogeneous domains demonstrate ARIA's strong performance, interpretability, and efficiency compared with state-of-the-art systems. By combining AI for research and AI for science principles within a spec-driven architecture, ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery.