Large Language Model-Guided Scientific Discovery

Autonomous experimentation has transformed microscopy and materials discovery by enabling closed-loop optimization including imaging and spectroscopy tuning, strucutre property relationship discovery, and exploration of combinatorial libraries. However, most current workflows remain limited to selecting measurements within fixed objective or hypothesis spaces, rather than generating new physical models from experimental data. Here, we introduce an open hypothesis-learning framework that combines symbolic regression with large-language-model-based physical evaluation and implement it for autonomous scanning probe microscopy. Symbolic regression generates candidate analytical relationships directly from sparse measurements, while the language-model evaluator ranks these candidates according to physical plausibility, scaling behavior, and consistency with known mechanisms. We demonstrate the approach on autonomous piezoresponse force microscopy measurements of ferroelectric domain switching in a PZT thin film. Starting from five seed measurements, the workflow evolves from physically incomplete candidate expressions toward interpretable voltage-time growth laws consistent with kinetic domain-wall motion. This work extends autonomous microscopy from closed-loop optimization toward open hypothesis discovery, where candidate physical laws emerge from the experiment itself rather than being specified in advance. More broadly, the framework establishes a route for integrating symbolic regression, physical reasoning, and adaptive experimentation into hierarchical autonomous scientific workflows.

As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical question emerges: How does the interaction between researchers and agents affect the results? We study this using SCALAR (Structured Critic--Actor Loop for AI Reasoning), an Actor--Critic--Judge pipeline applied to quantum field theory and string theory problems. The Actor proposes solutions, the Critic provides iterative feedback, and an independent Judge evaluates the transcript against reference solutions. We vary the Actor persona, the Critic feedback strategy, and the Actor model family and scale. Multi-turn dialogue improves over single-shot attempts throughout, but both the mechanism of improvement and the value of different prompting choices depend strongly on the Actor--Critic pairing. Increasing the scale within one model family (e.g. from the 8B-parameter DeepSeek-R1 variant to DeepSeek-R1 70B) improves some easier-problem behavior, but does not remove the hardest bottleneck we observe. Critic feedback strategy matters most clearly in the asymmetric Actor--Critic setting (e.g., a lightweight Haiku Actor guided by a stronger Sonnet Critic), where constructive feedback improves mean-score outcomes. In same-family Actor--Critic settings, strategy effects are weaker: lenient feedback is sometimes favored, while strict and adversarial feedback are not beneficial. Taken together, SCALAR provides a controlled testbed for evaluating which interaction structures help or hinder AI-driven scientific discovery.

The development of accurate exchange-correlation (XC) functionals remains a longstanding challenge in density functional theory (DFT). The vast majority of XC functionals have been hand designed by human researchers combining physical insight, exact constraints, and empirical fitting. Recent advances in large language models enable a systematic, automated alternative to this human-driven design loop. This report presents an agentic search system in which an LLM proposes structured functional-form changes guided by evolutionary history. The system attempts to improve functional performance through an iterative plan-execute-summarize loop, where improvements are measurable by optimizing functional parameters against a standard thermochemistry dataset, then evaluating performance on a held-out subset. The strongest discovered functional, SAFS26-a (Seed Agentic Functional Search 2026), improves upon the gold-standard ωB97M-V baseline by ~9%. These results also surface a cautionary lesson for AI-assisted science: models powerful enough to discover genuine improvements are equally capable of exploiting unphysical shortcuts to game the benchmark; domain expertise translated into explicitly enforced constraints remains essential to keeping results scientifically grounded.

LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is difficult to pinpoint the weaknesses in the generated ideas and how the agents refine them. To this end, we introduce \textbf{Evolving Idea Graphs} (EIG), a graph-based multi-agent scientific ideation framework that can generate high-performance research ideas across various benchmark-native metrics, such as novelty, feasibility, and clarity. Instead of coordinating solely through texts, EIG represents a partially formed proposal as an evolving idea graph, where nodes capture scientific claims and edges encode relations (e.g., support and conflict), enabling unresolved weaknesses to remain identifiable throughout the idea evolving process. Specifically, a learned two-head controller operates over the evolving graph to guide the ideation: one head selects graph edits for agents to execute, while the other decides when the graph is ready for commit as final proposal synthesis. On AI Idea Bench 2025 and LiveIdeaBench, EIG outperforms all compared systems on both automatic benchmark scores and blind expert ratings. Ablations further show that explicit graph state provides the main performance gains, and learned edit-and-commit control adds consistent improvements.

Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional approaches, primarily based on genetic algorithms and related evolutionary methods, have proven useful but suffer from scalability and expressivity limitations. Recently, large language model (LLM)-based evolutionary search methods have been introduced into SR and show promise. However, existing LLM-based approaches typically rely on scalar evaluation metrics, such as mean squared error, as the sole source of feedback during the search process, thereby overlooking the rich information embedded in the dataset. To address this limitation, we propose a novel LLM-based evolutionary search framework that incorporates programmatic context augmentation. By enabling code-based interactions with the dataset, our method can actively perform data analysis and extract informative signals, beyond aggregated evaluation scores. We evaluate our framework on advanced benchmarks, such as LLM-SRBench, and demonstrate superior efficiency and accuracy compared to strong baselines.

Large Language Models (LLMs) are increasingly being used to support scientific discovery. In chemistry, tasks such as reaction prediction and structure elucidation require reasoning about the structures of molecules. As such, LLM-based systems for chemistry must interact reliably with molecular structures. Most previous studies of LLMs in chemistry have used SMILES strings or IUPAC names as molecular representations; however, the suitability of these formats has not been systematically assessed. In this work, we introduce MolJSON, a novel molecular representation for LLMs, and systematically compare it with five common chemical formats. We evaluated each representation with GPT-5-nano, GPT-5-mini, GPT-5, and Claude Haiku 4.5 using a set of 78,045 questions spanning translation, shortest path, and constrained generation reasoning tasks. We observed substantial variation across representations in the ability of LLMs to interpret and generate molecular graphs, with MolJSON consistently outperforming existing formats. On translation tasks, GPT-5 achieved 71.0% accuracy when converting IUPAC names to MolJSON, compared with 43.7% when converting the same inputs to SMILES. For constrained generation, GPT-5 reached 95.3% accuracy generating MolJSON, compared with 76.3% for IUPAC and 64.0% for SMILES. As an input format for shortest-path reasoning, GPT-5 successfully answered 98.5% of questions with MolJSON, compared with 92.2% for SMILES and 82.7% for IUPAC, whilst also using fewer reasoning tokens. We observed systematic errors associated with atom count and ring complexity for SMILES strings and IUPAC names, whereas MolJSON was more robust to these failure modes. Our results show that the choice of molecular representation has a material impact on LLM performance, and that explicit molecular graph schemas, such as MolJSON, are a promising direction for LLM-based systems in chemistry.

Scientific discovery is an extended process of ideation--surveying prior work, forming hypotheses, and refining reasoning--yet existing approaches treat this phase as a brief preamble despite its central role in research. We introduce SCISENSE, a sensemaking-grounded framework that operationalizes ideation as a structured sequence of eight cognitive stages (Pirolli & Card, 2005). We construct SCISENSE-Traj, a 100K-scale dataset of citation-conditioned research trajectories in two modes: Target, where an LLM reconstructs the ideation path leading to a known paper from its cited works, and Infer, where the LLM proposes novel directions from the same citations. We distill these into SCISENSE-LM, a family of sensemaking LLMs spanning 3B to 70B parameters. Contrary to the assumption that looser supervision promotes greater exploration, Target-trained models achieve a 2.0% improvement in trajectory quality over Infer-trained models while also producing more novel and diverse outputs. This advantage propagates downstream: coding agents conditioned on Target trajectories produce research artifacts with higher executability and quality than those conditioned on Infer trajectories. This suggests that targeted ideation reduces cognitive burden on downstream agents, freeing them to explore more creatively. SCISENSE offers both a practical tool for augmenting LLM-driven research workflows and a principled testbed for studying how planning shapes scientific discovery.

Deep learning in \emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or interactions are functionally essential. As a result, design decisions are entangled with continuous sampling dynamics, limiting interpretability, controllability, and systematic reuse of biochemical knowledge. We introduce \textbf{Proteo-R1}, a reasoning-guided protein design framework that explicitly decouples \emph{molecular understanding} from \emph{geometric generation}. Proteo-R1 adopts a dual-expert architecture in which a multimodal large language model (MLLM) serves as an \emph{understanding expert}, analyzing protein sequences, structures, and textual context to identify key functional residues that govern binding and specificity. These residue-level decisions are then passed as hard constraints to a separate diffusion-based \emph{generation expert}, which performs conditional co-design while respecting the fixed interaction anchors. This factorization mirrors how human experts approach molecular engineering: first, reasoning about critical interactions, then optimizing geometry subject to those constraints. By operationalizing reasoning as explicit residue-level commitments rather than latent textual guidance, Proteo-R1 achieves stable, interpretable, and modular integration of LLM reasoning with state-of-the-art geometric generative models. Code, data, and demos are available at https://smiles724.github.io/r1/.

When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective? We introduce DriftBench, a benchmark for evaluating constraint adherence in multi-turn LLM-assisted scientific ideation. Across 2,146 scored benchmark runs spanning seven models from five providers (including two open-weight), four interaction conditions, and 38 research briefs from 24 scientific domains, we find that iterative pressure reliably increases structural complexity and often reduces adherence to original constraints. A restatement probe reveals a dissociation between declarative recall and behavioral adherence, as models accurately restate constraints they simultaneously violate. The knows-but-violates (KBV) rate, measuring constraint non-compliance despite preserved recall, ranges from 8% to 99% across models. Structured checkpointing partially reduces KBV rates but does not close the dissociation, and complexity inflation persists. Human validation against blind raters confirms that the LLM judge under-detects constraint violations, making reported constraint adherence scores conservative. Sensitivity analyses confirm the findings are robust to temperature (0.7 vs.\ 1.0) and pressure type (novelty vs.\ rigor). We release all briefs, prompts, rubrics, transcripts, and scores as an open benchmark.

A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive system designed to translate abstract intuitions into executable computational experiments. Grounded in a domain-specific knowledge base covering over 13,000 high-quality academic papers, the system employs a modular multi-stage architecture. Specifically, the Idea Development Stage generates literature-grounded hypotheses, the Experimental Design Stage configures simulator-aligned experimental parameters and protocols, and the Experimental Execution Stage runs experiments and returns structured analyses. Together, these stages form a human-in-the-loop, iterative workflow that translates economic intuitions into executable computational experiments. Through extensive experiments involving human expert evaluation and large language models (LLMs) as judges, we show that the system generates research ideas with stronger literature grounding and higher novelty and insight than state-of-the-art generic LLMs. Overall, AgentEconomist adopts a human-AI collaboration paradigm that enables researchers to focus on high-level intuitions, while delegating the labor-intensive processes of translation and computational execution to agents.

Metamaterial discovery seeks microstructured materials whose geometry induces targeted mechanical behavior. Existing inverse-design methods can efficiently generate candidates, but they typically require explicit numerical property targets and are less suitable for early-stage exploration, where researchers often begin with incomplete constraints and qualitative intents expressed in natural language. Large language models can interpret such intents, but they lack geometric awareness and physical property validity. To address this gap, we propose MetaSymbO, a multi-agent framework for language-guided Metamaterial discovery via Symbolic-driven latent evOlution. Specifically, MetaSymbO contains three agents: a Designer that interprets free-form design intents and retrieves a semantically consistent scaffold, a Generator that synthesizes candidate microstructures in a disentangled latent space, and a Supervisor that provides fast property-aware feedback for iterative refinement. To move beyond the limitations of reproducing known samples from literature and training data, we further introduce symbolic-driven latent evolution, which applies programmable operators over disentangled latent factors to compose, modify, and refine structures at inference time. Extensive experiments demonstrate that (i) MetaSymbO improves structural validity by up to 34% in symmetry and nearly 98% in periodicity compared to state-of-the-art baselines; (ii) MetaSymbO achieves about 6-7% higher language-guidance scores while maintaining superior structure novelty compared to advanced reasoning LLMs; (iii) qualitative analyses confirm the effectiveness of symbolic logic operators in enabling programmable semantic alignment; and (iv) realworld case studies on auxetic, high-stiffness metamaterial design further validate its practical capability.

Artificial intelligence has accelerated materials discovery through high-throughput prediction and generation, yet the decision problem remains a formidable bottleneck. While current AI systems readily propose millions of candidates, navigating the decision regarding a viable experimental target requires resolving multi-dimensional judgments across atomic-scale numerical computation and high-level semantic reasoning. Here we present ElementsClaw, an agentic framework for materials discovery that orchestrates a suite of Large Atomic Model (LAM) tools finetuned from our proposed 1-billion-parameter model Elements for numerical computation, while leveraging Large Language Models (LLMs) for semantic reasoning. Applied to superconductors, ElementsClaw rediscovers 66 experimentally verified superconductors that are absent from the standard SuperCon3D database. Scaling to 2.4 million equilibrium crystals, ElementsClaw identifies 68,000 high-confidence candidates in just 28 GPU hours (https://developer.damo-academy.com/material), expanding known superconducting space by orders of magnitude compared to datasets curated over decades. Guided by the agent's reasoning, we experimentally synthesize and verify four novel superconductors: the motif-guided Zr$_3$ScRe$_8$ ($T_c$ = 6.5 K), the de novo generated HfZrRe$_4$ ($T_c$ = 5.9 K), the structurally reinterpreted Zr$_4$VRe$_7$ ($T_c$ = 3.5 K), and the database-latent Hf$_{21}$Re$_{25}$ ($T_c$ = 2.5 K). Together, our results establish a knowledge integrated, autonomously orchestrated, and experimentally grounded paradigm for materials discovery.

Ramsey-good graphs are graphs that contain neither a clique of size $s$ nor an independent set of size $t$. We study doubly saturated Ramsey-good graphs, defined as Ramsey-good graphs in which the addition or removal of any edge necessarily creates an $s$-clique or a $t$-independent set. We present a method combining SAT solving with bespoke LLM-generated code to discover infinite families of such graphs, answering a question of Grinstead and Roberts from 1982. In addition, we use LLMs to generate and formalize correctness proofs in Lean. This case study highlights the potential of integrating automated reasoning, large language models, and formal verification to accelerate mathematical discovery. We argue that such tool-driven workflows will play an increasingly central role in experimental mathematics.

Discovering materials that must simultaneously satisfy multiple competing constraints remains a central challenge in computational materials design, particularly in data-scarce regimes where conventional data-driven approaches are least effective. Magnetic insulators represent a stringent example: the electronic conditions that favor magnetic order often also promote metallicity, while insulating behavior suppresses the interactions that stabilize magnetism. As a result, experimentally viable magnetic insulators are rare and difficult to identify through conventional screening. Here, we introduce MagMatLLM, a constraint-guided generative discovery framework that integrates language-model-based crystal generation with evolutionary selection, surrogate screening, and first-principles validation to target simultaneous stability, magnetism, and insulating behavior. Unlike stability-first approaches, the framework enforces functional constraints during generation and selection, steering the search toward sparsely populated regions of materials space defined by competing physical requirements. Using this workflow, we identify twelve previously unreported candidate magnetic insulators, including Tm$_4$Co$_2$Cr$_2$O$_{12}$ and Cr$_4$Nb$_2$O$_{12}$. Of these, ten are dynamically stable by phonon analysis and exhibit finite band gaps and nonzero magnetic moments in spin-polarized density functional theory calculations. Beyond the specific compounds identified here, this work establishes a general constraint-guided paradigm for multi-objective materials discovery in sparse chemical spaces and provides a transferable strategy for the design of quantum materials under competing physical constraints.

The most technologically consequential materials are often the rarest: they occupy narrow regions of chemical space, obey competing physical constraints, and appear only sparsely in existing databases. High-kappa dielectrics, high-Tc superconductors, and ferromagnetic insulators are to name a few. This scarcity fundamentally limits today's data-driven materials discovery, where machine-learning models excel at interpolation but struggle to generate genuinely new candidates. Here, we introduce DielecMIND, an artificial intelligence framework that reframes materials discovery as a reasoning-driven exploration instead of a database-screening problem. Using high-kappa dielectrics as a data-scarce and technologically stringent test case, DielecMIND combines large-language-model hypothesis generation for the first time with physics validated first-principles calculation to navigate chemical space beyond known compounds. Prior to our work, only 14 experimentally or computationally validated materials with kappa > 150 were known. Our framework discovers and validates 5 new such compounds, expanding this rare-materials class by a remarkable = 35% in a single study. Among them, we find that Ba2TiHfO6 exhibits a dielectric constant of 637, minimal loss at low optical frequencies, and stability up to 800 K. Beyond dielectrics, this work demonstrates a new paradigm for artificial-intelligence-guided discovery: one that generates a small number of physically grounded, experimentally plausible candidates yet measurably expands sparsely populated functional materials spaces. Thus, DielecMIND points toward a general strategy for discovering rare, high-impact functional materials where data scarcity has long constrained progress.

Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify novel directions. Although existing large language model (LLM)-based methods show promise in research idea generation, the ideas they produce are often repetitive and lack depth. To address this issue, this study proposes a multi-agent iterative planning search strategy inspired by com-binatorial innovation theory. The framework combines iterative knowledge search with an LLM-based multi-agent system to generate, evaluate, and re-fine research ideas through repeated interaction, with the goal of improving idea diversity and novelty. Experiments in the natural language processing domain show that the proposed method outperforms state-of-the-art base-lines in both diversity and novelty. Further comparison with ideas derived from top-tier machine learning conference papers indicates that the quality of the generated ideas falls between that of accepted and rejected papers. These results suggest that the proposed framework is a promising approach for supporting high-quality research idea generation. The source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas. The demo is available at https://huggingface.co/spaces/cshuai20/MAGenIdeas.

Constructing phase diagrams for multicomponent alloys requires extensive experimental measurements and is a time-consuming task. Here we investigate whether large language models (LLMs) can guide experimental planning for phase diagram construction. In our framework, a general-purpose LLM serves as the experimental planner, suggesting compositions for measurement at each cycle in a closed loop with high-throughput synthesis and X-ray diffraction phase identification. Using this framework, we experimentally constructed the ternary phase diagram of the Co-Al-Ge system at 900 degree C through iterative synthesis and characterization. We compared two strategies that differ in how the initial compositions are selected: one uses predictions from a domain-specific LLM trained on phase diagram data (aLLoyM), while the other relies solely on the general-purpose LLM. The two strategies exhibited complementary strengths. aLLoyM directed the initial measurements toward compositionally complex regions in the interior of the ternary diagram, enabling the earliest discovery of all three novel phases that form only in the ternary system. In contrast, the general-purpose LLM adopted a textbook-like approach which efficiently identified a larger number of phases in fewer cycles. In addition, a simulated benchmark comparing the LLM against conventional machine learning confirmed that the LLM achieves more efficient exploration. The results demonstrate that LLMs have high potential as experimental planners for phase diagram construction.

Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively refine them. At the core of these trial-and-error loops lies evaluation: the process of obtaining feedback on candidate solutions via verifiers, simulators, or task-specific scoring functions. While prior work has highlighted the importance of evaluation, it has not explicitly formulated the problem of how evaluation-driven discovery loops can be scaled up in a principled and effective manner to push the boundaries of scientific discovery, a problem this paper seeks to address. We introduce Simple Test-time Evaluation-driven Scaling (SimpleTES), a general framework that strategically combines parallel exploration, feedback-driven refinement, and local selection, revealing substantial gains unlocked by scaling evaluation-driven discovery loops along the right dimensions. Across 21 scientific problems spanning six domains, SimpleTES discovers state-of-the-art solutions using gpt-oss models, consistently outperforming both frontier-model baselines and sophisticated optimization pipelines. Particularly, we sped up the widely used LASSO algorithm by over 2x, designed quantum circuit routing policies that reduce gate overhead by 24.5%, and discovered new Erdos minimum overlap constructions that surpass the best-known results. Beyond novel discoveries, SimpleTES produces trajectory-level histories that naturally supervise feedback-driven learning. When post-trained on successful trajectories, models not only improve efficiency on seen problems but also generalize to unseen problems, discovering solutions that base models fail to uncover. Together, our results establish effective evaluation-driven loop scaling as a central axis for advancing LLM-driven scientific discovery, and provide a simple yet practical framework for realizing these gains.

Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science.To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent.

Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational inefficiency. A critical bottleneck in applying Reinforcement Learning (RL) to this open-ended domain is reward hacking -- where models exploit imperfect evaluation proxies to maximize scores without producing genuine scientific innovation. To address these limitations, we propose an RL framework explicitly tailored for high-quality scientific idea generation. We propose the first multi-agent reward function designed to serve as a judge, decoupling methodological validation from implementation details while providing strict binary rewards that are robust to reward hacking. To effectively optimize against this sparse signal, we utilize an unbiased variant of Group Relative Policy Optimization to mitigate artificial length bias. We grounded our training in ICLR-320, a curated dataset of problem-solution pairs extracted from ICLR 2024 proceedings. Experiments demonstrate that our framework significantly outperforms state-of-the-art baselines across expert-evaluated metrics of novelty, feasibility, and effectiveness.

Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. Across benchmark datasets, DrugKLM outperforms knowledge graph-only and language model-only baselines, including TxGNN. Beyond improved recall, DrugKLM confidence scores exhibit functional alignment with molecular phenotypes: higher scores are associated with transcriptional signatures linked to improved survival across 12 TCGA cancers. The scoring framework preferentially captures biologically perturbational signals rather than historical indication patterns. Expert curation across five cancers further reveals systematic differences in prioritization behavior, with DrugKLM elevating candidates supported by coherent mechanistic rationale and disease-specific clinical context. Together, these results establish DrugKLM as an evidence-integrative framework that translates heterogeneous biomedical data into mechanistically interpretable and clinically grounded therapeutic hypotheses.

The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension and complex reasoning, failing to evaluate the exploratory nature and procedural complexity of real-world research. In this work, we present research-oriented evaluations in theoretical and computational physics, a natural testbed with comprehensive domain knowledge, complex reasoning, and verifiable end-to-end workflows without reliance on experiments. Here we introduce PRL-Bench (Physics Research by LLMs), a benchmark designed to systematically map the capability boundaries of LLMs in executing end-to-end physics research. Constructed from 100 curated papers from the latest issues of Physical Review Letters since August 2025 and validated by domain experts, PRL-Bench covers five major theory- and computation-intensive subfields of modern physics: astrophysics, condensed matter physics, high-energy physics, quantum information, and statistical physics. Each task in the benchmark is designed to replicate the core properties of authentic scientific research, including exploration-oriented formulation, long-horizon workflows, and objective verifiability, thereby reconstructing the essential reasoning processes and research workflows of real physics research. Evaluation across frontier models shows that performance remains limited, with the best overall score below 50, revealing a pronounced gap between current LLM capabilities and the demands of real scientific research. PRL-Bench serves a reliable testbed for accessing next generation AI scientists advancing AI systems toward autonomous scientific discovery.

Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research. Existing LLM-driven scientific discovery systems are typically limited to one-shot prompting on static literature snapshots and are validated only against contemporary judges such as human reviewers, agent peer review, wet-lab assays, or self-evaluation, leaving open whether they can anticipate future trends. We present Continuous Knowledge Metabolism (CKM), an AI workflow for hypothesis generation with three key capabilities: (i) continuous literature metabolism via sliding windows that maintain an evolving knowledge state; (ii) predictive evaluation, which grades hypotheses against papers published after the generation window; and (iii) practitioner-grade failure detection that diagnoses workflow failure modes from its outputs. On a 50-topic machine learning benchmark, CKM-Lite produces at least one validated hypothesis on 72% of topics (36 out of 50), more than doubling a one-shot baseline (30%) at approximately 3 dollars per topic and achieving 91% lower token cost. Validated hypotheses precede their matched papers by an average of 404 days (55 hits across 36 topics; median 399 days, range 66-757 days). Broadly, predictive validation against future literature provides a falsifiable, low-cost alternative to contemporary-judge evaluation protocols and can be applied wherever a corpus has dated publication records.

Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale human evaluation is costly. We propose a verifiable alternative by reframing proposal generation as a time-sliced scientific forecasting problem. Given a research question and inspiring papers available before a cutoff time, the model generates a structured proposal and is evaluated by whether it anticipates research directions that appear in papers published after the time. We operationalize this objective with the Future Alignment Score (FAS), computed via retrieval and LLM-based semantic scoring against a held-out future corpus. To train models, we build a time-consistent dataset of 21,835 paper occurrences across 3,642 instances from targets and their pre-cutoff citations, and synthesize reasoning traces that teach gap identification and inspiration borrowing. Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method. Our code and data are publicly available at https://github.com/Arthur-Heng/future-aligned-proposals.

The discovery of catalysts for electrochemical applications such as the oxygen reduction reaction (ORR), nitrogen reduction reaction (NRR), and CO2 reduction reaction (CO2RR) remains a central challenge in chemistry and materials science. Machine-learning interatomic potentials (MLIPs) and graph neural network models now accelerate individual adsorption-energy calculations by orders of magnitude relative to density functional theory. However, true large-scale screening is still blocked by human decisions: selecting candidates, constructing slabs, enumerating adsorption sites, interpreting descriptor failures, and choosing follow-up modifications. Here, we introduce Catalyst-Agent, a Model Context Protocol (MCP) server-based, LLM-powered agent that autonomously coordinates closed-loop catalyst screening. Catalyst-Agent searches materials databases through OPTIMADE, constructs slabs, computes adsorption energies using Meta FAIRchem's UMA MLIP within AdsorbML, evaluates reaction-specific descriptors, and applies structural modifications to refine near-miss candidates. In ORR, NRR, and CO2RR campaigns, Catalyst-Agent demonstrates high performance and converges in 1.40-3.41 trials per successful material on average. It identified Sn3Sc, Sn3Y, Tl3La, Pb3Y and In3Y as CO2RR candidates for further validation that were not previously reported in the literature. DFT single-point checks confirmed screening outcomes for representative NRR and CO2RR candidates. Ablations show these gains arise from chemically informed candidate selection and feedback-directed modification rather than brute-force evaluation: fully randomized screening dropped to 13.3%, 16.7%, and 0% success for ORR, NRR, and CO2RR, respectively. These results show that tool-grounded LLM agents can shift catalyst screening from manual trial-and-error toward more autonomous, reproducible and adaptive workflows.

Automated methods for discovering mechanistic simulator models from observational data offer a promising path toward accelerating scientific progress. Such methods often take the form of agentic-style iterative workflows that repeatedly propose and revise candidate models by imitating human discovery processes. However, existing LLM-based approaches typically implement such workflows via hand-crafted heuristic procedures, without an explicit probabilistic formulation. We recast model discovery as probabilistic inference, i.e., as sampling from an unknown distribution over mechanistic models capable of explaining the data. This perspective provides a unified way to reason about model proposal, refinement, and selection within a single inference framework. As a concrete instantiation of this view, we introduce ModelSMC, an algorithm based on Sequential Monte Carlo sampling. ModelSMC represents candidate models as particles which are iteratively proposed and refined by an LLM, and weighted using likelihood-based criteria. Experiments on real-world scientific systems illustrate that this formulation discovers models with interpretable mechanisms and improves posterior predictive checks. More broadly, this perspective provides a probabilistic lens for understanding and developing LLM-based approaches to model discovery.

LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evolve a monolithic program that directly outputs a candidate solution. We present ImprovEvolve, an algorithmic alternative that drastically reduces cognitive load on the LLM. Instead of prompting the model for an end-to-end optimizer, we evolve a program with three specialized operators of initialization, local improvement, and perturbation. We then approach the optimum by iteratively applying local improvements and intensity-scheduled perturbations, effectively driving a basin-hopping search with LLM-evolved subroutines. For hexagon in hexagon packing, ImprovEvolve discovers new state-of-the-art packings of 11, 12, 15, and 16 hexagons, and additionally for 14, 17, and 23 hexagons after minimal expert tuning of the generated code. For the second autocorrelation inequality, the evolved and human-scaled program pushes the lower bound from 0.96102 to 0.96258. For spherical codes, the ImprovEvolve program lowers the best-known maximum cosine for the majority of 90 randomly chosen diverse state-of-the-art spherical codes, achieving relative improvements of up to 2.4%.

The Gilbert-Pollak Conjecture \citep{gilbert1968steiner}, also known as the Steiner Ratio Conjecture, states that for any finite point set in the Euclidean plane, the Steiner minimum tree has length at least $\sqrt{3}/2 \approx 0.866$ times that of the Euclidean minimum spanning tree (the Steiner ratio). A sequence of improvements through the 1980s culminated in a lower bound of $0.824$, with no substantial progress reported over the past three decades. Recent advances in LLMs have demonstrated strong performance on contest-level mathematical problems, yet their potential for addressing open, research-level questions remains largely unexplored. In this work, we present a novel AI system for obtaining tighter lower bounds on the Steiner ratio. Rather than directly prompting LLMs to solve the conjecture, we task them with generating rule-constrained geometric lemmas implemented as executable code. These lemmas are then used to construct a collection of specialized functions, which we call verification functions, that yield theoretically certified lower bounds of the Steiner ratio. Through progressive lemma refinement driven by reflection, the system establishes a new certified lower bound of 0.8559 for the Steiner ratio. The entire research effort involves only thousands of LLM calls, demonstrating the strong potential of LLM-based systems for advanced mathematical research.

AI-Scientist systems risk manufacturing spurious discoveries through uncontrolled multiple testing. We present a functional architecture that enforces statistical rigor at two levels: a Haskell embedded domain-specific language (the Research monad) that makes it impossible to test a hypothesis without updating the error budget, and a declarative scaffold, backed by an OS-level sandbox, that makes validation data physically absent from the environment in which LLM-generated code runs. We ground the design in a machine-checked Lean4 formalization of LORD++ online false-discovery-rate (FDR) control: we derive its error budget and prove both marginal and full FDR control, then close the gap to the implementation by verifying the budget's wealth invariant over IEEE754 arithmetic in SPARK/Ada. To our knowledge this is the first verified chain from theorem to floating-point implementation for an online FDR procedure. In simulation, the architecture holds the false discovery rate near 1% against a 5% target, where a naive approach reaches 41%. In end-to-end case studies, a valid test avoids the false discoveries a flawed one produces, yet still finds real effects when the data allow. An adversarial evaluation confirms that generated code cannot read the held-out data even when given its exact path.

The process of scientific discovery relies on an interplay of observations, analysis, and hypothesis generation. Machine learning is increasingly being adopted to address individual aspects of this process. However, it remains an open challenge to fully automate the heuristic, iterative loop required to discover the laws of an unknown system by exploring it through experiments and analysis, without tailoring the approach to the specifics of a given task. Here, we introduce SciExplorer, an agent that leverages large language model tool-use capabilities to enable exploration of systems without any domain-specific blueprints, and apply it to physical systems that are initially unknown to the agent. We test SciExplorer on a broad set of models spanning mechanical dynamical systems, wave evolution, and quantum many-body physics. Despite using a minimal set of tools, primarily based on code execution, we observe impressive performance on tasks such as recovering equations of motion from observed dynamics and inferring Hamiltonians from expectation values. The demonstrated effectiveness of this setup opens the door toward similar scientific exploration in other domains, without the need for fine-tuning or task-specific instructions.