Large Language Model-Guided Scientific Discovery

A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding. Statistical models excel on structured data but operate as black boxes, while existing interpretability methods are largely inspective: they answer "which features matter?" but do not articulate how features interact or refine explanations iteratively alongside human understanding. Asking an LLM to predict the target directly forces it to search the entire output space; we instead anchor predictions with a base model and ask the LLM the narrower question of what that model is missing. We introduce Multi-Agent Residual In-Context Learning (MARICL), an agentic framework in which LLM agents analyze where a base-model fails, hypothesize missing structure from high-residual examples provided in context, and produce explicit correction terms refined through multi-turn textual gradient optimization. Across nine benchmarks spanning scientific, biomedical, socioeconomic, and synthetic settings, MARICL improves consistently over its base model on all datasets. To test whether these corrections reflect real structure or batch-specific noise, we freeze formulas learned on one experimental batch of the Cell-Free Protein dataset and apply them (with no retraining and no further LLM calls) to held-out batches. Within the same reagent protocol, the frozen formulas improve predictions in over 92% of cases; across a different protocol, they fail systematically. The success boundary aligns with the biochemistry, not the batch count; direct evidence of mechanistic generalization.

Large Language Models (LLMs) are central to the one-for-all intelligent paradigm, but they face a fundamental challenge when dealing with heterogeneous scientific data such as molecules: the inherent gap between discrete linguistic symbols and topological molecular or continuous reaction data leads to significant information loss and semantic noise in text-based reasoning. We propose SciCore-Mol, a modular framework that bridges this gap through three deeply integrated pluggable cognitive modules: a topology-aware perception module, a latent diffusion-based molecular generation module, and a reaction-aware reasoning module. Each module is coupled to the LLM backbone through learned representation interfaces, enabling richer information exchange than is possible with text-only tool feedback. Our experiments on diverse chemical tasks demonstrate that SciCore-Mol achieves strong comprehensive performance across molecular understanding, generation, reaction prediction, and general chemistry knowledge, with an 8B-parameter open-source system that is competitive with and in several dimensions surpasses proprietary large models. This work provides a systematic blueprint for equipping LLMs with scientific expertise through decoupled, pluggable, and flexibly orchestrated modules, with direct implications for drug design, chemical synthesis, and broader scientific discovery.

The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). However, existing approaches typically embed LLMs directly into the sampling or surrogate modeling pipeline, without fully leveraging their significantly lower evaluation cost compared to real-world experiments. To address this limitation, we propose LLM-Accelerated Bayesian Optimization (LABO), a framework that combines LLM predictions with experimental observations within a single BO loop. LABO employs a gating criterion to dynamically balance the reliance on LLM predictions versus actual experiments. By leveraging inexpensive LLM evaluations to broadly explore the search space and reserving costly real experiments only for regions with high uncertainty, LABO achieves more sample-efficient optimization. We provide a theoretical analysis with a cumulative regret bound that formalizes this efficiency gain. Empirical results across diverse scientific tasks demonstrate that LABO consistently outperforms existing methods under identical experimental budgets. Our results suggest that LABO offers a practical and theoretically grounded approach for integrating LLMs into scientific discovery workflows.

Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large language model-based pipelines; however, existing frameworks remain limited to textual and tabular content, overlooking the substantial proportion of quantitative property data reported exclusively in scientific figures. Here, we extend ComProScanner, a fully end-to-end multi-agent framework for automated composition-property database construction, with a native vision-language model (VLM) based figure extraction capability. The extension introduces a FigureExtractor utility for caption-keyword-based figure filtering across all supported publishers, and a GraphExtractorTool agent that passes extracted figures to a configurable VLM to recover composition-property pairs from scientific charts and plots. Four VLMs are selected for evaluation on the basis of the LMArena Diagram leaderboard with an input cost criterion of less than $1.50 per million tokens. Benchmarking on 50 piezoelectric ceramic articles from the established $d_{33}$ test corpus demonstrates that Gemini-3-Flash-Preview achieves the highest performance with a composition accuracy of 0.97 and a normalised F1 score of 0.97, whilst remaining the most cost-effective model among the four evaluated. We additionally introduce a range-based value error threshold parameter into the evaluation framework, providing a more physically meaningful assessment of numeric property values extracted from figures than exact value matching. These contributions establish VLM-integrated ComProScanner as the first materials-specific, fully automated, multimodal literature mining platform capable of extracting structured composition-property data from text, tables, and figures within a single unified pipeline.

Nanomedicine research spans delivery chemistry, immunology, imaging, biomaterials, and disease-specific translational science, yet its conceptual design space remains fragmented across a large and heterogeneous literature. To date, artificial intelligence in nanomedicine has focused primarily on property prediction and formulation optimization, with much less attention to evidence-grounded discovery support at the level of research direction selection. We introduce pArticleMap, a literature-mapping and research-hypothesis-generation system that combines article embeddings, similarity-graph analysis, sparse frontier extraction, structured evidence-pack retrieval, and an audited large-language-model (LLM) workflow for grounded ideation. Rather than forecasting future concept co-occurrence, pArticleMap targets low-density article-level bridge regions and cluster interfaces, then generates and scores citation-grounded hypotheses with large language models in an agentic setup. We evaluate the system with a retrospective realization benchmark (generate later literature under a historical cutoff) and a blinded human reader assessment layer across cue-conditioned nanomedicine tasks. Across 4 selected retrospective bundles, pArticleMap generated ideas and selected task-retained hypotheses (winner ideas) under the benchmark protocol. For task-level retained hypotheses, a pooled gold recovery rate of 10.8% was obtained, with a recall@10 of 15.9% and a future-neighborhood rate of 61.0%, indicating that the system often reached the correct forward-looking neighborhood (paper ideas) even without exact paper-level recovery. Human-agent agreement is modest overall, indicating that internal scoring is useful as a support signal but does not replace expert judgment. These results position pArticleMap as a conservative, evidence-grounded research assistant for nanomedicine.

Scientific discovery is increasingly constrained by costly experiments and limited resources, underscoring the need for efficient optimization in AI for science. Bayesian Optimization (BO), though widely adopted for balancing exploration and exploitation, often exhibits slow cold-start performance and poor scalability in high-dimensional settings, limiting its applicability in real-world scientific problems. To overcome these challenges, we propose LLM-Guided Bayesian Optimization (LGBO), the first LLM preference-guided BO framework that continuously integrates the semantic reasoning of large language models (LLMs) into the optimization loop. Unlike prior works that use LLMs only for warm-start initialization or candidate generation, LGBO introduces a region-lifted preference mechanism that embeds LLM-driven preferences into every iteration, shifting the surrogate mean in a stable and controllable way. Theoretically, we prove that LGBO does not perform significantly worse than standard BO in the worst case, while achieving significantly faster convergence when preferences align with the objective. Empirically, LGBO consistently outperforms existing methods across diverse dry benchmarks in physics, chemistry, biology, and materials science. Most notably, in a new wet-lab optimization of Fe-Cr battery electrolytes, LGBO attains \textbf{90% of the best observed value within 6 iterations}, whereas standard BO and existing LLM-augmented baselines require more than 10. Together, these results suggest that LGBO offers a promising direction for integrating LLMs into scientific optimization workflows.

Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conventional trial-and-error screening inefficient. We develop LEAP(LLM-driven Exploration via Active Learning for Perovskites), an expert-in-the-loop closed framework that couples a domain-specialized large language model(LLM) with active learning for iterative additive prioritization. The LLM is trained to extract mechanism-relevant knowledge from the perovskite additive literature and to represent candidate molecules through interpretable descriptors, which are further integrated into a Bayesian optimization workflow for uncertainty-aware prioritization under low-data conditions. Benchmark results on unseen literature show that the domain-specialized model outperforms general-purpose models in mechanism-consistent reasoning. Experimental validation in an expert-in-the-loop proof-of-concept study suggests improved additive prioritization across three screening rounds, leading to average device PCEs of 20.13% and 20.87% for the later-round 6-CDQ- and 2-CNA-treated devices, respectively, compared with 19.25% for the control, with a champion PCE of 21.32%. These results provide preliminary evidence that literature-grounded mechanistic descriptors, when coupled with Bayesian optimization and expert feasibility review, can support mechanism-aware additive prioritization in perovskite photovoltaics.

As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly saturate even extended contexts with dense technical content, while monolithic approaches suffer from quadratic cost scaling and cognitive degradation. We evaluate a Dual Process Memory Architecture that decouples immediate episodic needs (constant 10-message window) from long-term consolidated knowledge (growing at approximately 3 tokens/message). Unlike prior social agent memory systems, our domain-specific consolidation addresses contradictory parameter evolution, multi-hop reasoning across experimental phases, and precise technical fact retention. Through large-scale evaluation spanning 15,000 messages with cross-model validation across six LLMs from three families (OpenAI, Anthropic, Google), totaling 1,440 queries, we establish three key findings. First, while full-context models fail at 10,000 messages due to context overflow, our system maintains 70-85% accuracy with 1-2 second latency using 62% fewer tokens (45,434 vs 120,000+ limit). Second, cross-model validation reveals architecture-level trade-offs independent of specific LLMs: Dual Process excels at numeric/temporal queries (65-90% accuracy) while RAG excels at historical retrieval (60-85%), suggesting complementary deployment strategies. Third, we identify a "Sim-to-Real" gap where synthetic tests maintain constant memory but realistic workflows exhibit linear growth (about 3 tokens/message), with consolidation quality emerging as the primary scalability bottleneck. The architecture successfully manages profiles with 14,000+ scientific facts (125k tokens), demonstrating that domain-specific memory consolidation enables sustained operation beyond full-context limits.

Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in which topology is implicit, forcing LLMs to reconstruct molecular structure before performing the requested chemical operation. Here we introduce MoleCode, an LLM-native, training-free, graph-explicit molecular language in which all molecular components are represented as typed entities with persistent identifiers and explicit relations. MoleCode makes molecular topology directly readable, editable and auditable within the language context, allowing an LLM to operate on structure rather than recover it from syntax. Across molecular reasoning, editing, generation and analysis tasks, this representational shift improves frontier LLMs most strongly when structural access is limiting: unfamiliar molecules, topology-sensitive operations, larger structures and repetitive polymers. It also changes how inference is allocated, replacing long reasoning traces devoted to implicit structural reconstruction with shorter, more chemically directed reasoning over explicit atoms and bonds. In molecular optimization, this enables localized, property-aligned edits that preserve structural similarity to the starting compounds. The same Subgraph--Node--Edge grammar extends beyond small molecules to polymers, Markush structures, mechanism-style transformations and interleaved scientific documents, including research articles and patent disclosures in which chemical information is distributed across text and images. These results suggest that the interface between scientific objects and LLMs should not treat structure as something to be decoded from text. When the object of reasoning is relational, the structure itself should be part of the language.

We present a case study for how AI coding systems can be used to generate novel scientific hypotheses. We combine a generic coding agent (Google's AntiGravity) with an LLM-driven tree search algorithm (Empirical Research Assistance / ERA) to autonomously generate high-efficiency three-dimensional photovoltaic (3DPV) structures that overcome losses limiting flat solar panels at mid-latitudes. These structures operate by presenting favorable angles to the sun throughout the day, and for illustrative purposes we focus on optimizing performance for a single solar day. Our workflow begins by using AntiGravity to reproduce calculations \cite{bernardi2012solar} showing that 3DPV can have energy densities much higher than stationary flat PV panels. We use these initial designs as the starting point for large scale tree search, where we seek improved solutions and score them for their diurnal yield. The initial tree search leads to nominally more efficient solutions, yet they are caused by algorithmic reward hacking, arising from non-physical design features such as structurally levitating disconnected tiers and exploitations of the discretizations in the optics solver. To counteract this, we develop a workflow where the coding agent iteratively patches the physics engine with constraints to eliminate reward hacking. With reward-hacking eliminated, ERA discovers a series of designs with various constraints and improved performance, including optimal designs with different fixed collector areas, optimizing zenith tracking and avoiding self shadowing. Combining coding agents with tree search (ERA) provides a powerful platform for scientific discovery, for problems whose solutions can be empirically evaluated with a score function.

LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for designing their individual components and provide no guarantee that the search converges. We introduce SMCEvolve, which recasts program search as sampling from a reward-tilted target distribution and approximates it with a Sequential Monte Carlo (SMC) sampler. From this view, three core mechanisms emerge as principled components: adaptive parent resampling, mixture of mutation with acceptance, and automatic convergence control. We further provide a finite-sample complexity analysis that bounds the LLM-call budget required to reach a target approximation error. Across math, algorithm efficiency, symbolic regression, and end-to-end ML research benchmarks, SMCEvolve surpasses state-of-the-art evolving systems while using fewer LLM calls under self-determined termination. The code is available at https://github.com/kongwanbianjinyu/SMCEvolve.

Research idea generation is the innovation-driving step of automated scientific research. Recently, large language models (LLMs) have shown potential for automating idea generation at scale. However, existing methods mainly condition LLMs on eliciting idea generation through static retrieval of relevant literature or complex prompt engineering, without discarding the structural relations among references. We propose Graphs of Research (GoR), a supervised fine-tuning method that extracts a 2-hop reference neighborhood for each seed paper, derives the relations among those references from citation position, frequency, predecessor links, and publication time, and organizes them into a paper-evolution directed acyclic graph (DAG). We construct an automated extraction pipeline that draws data from five major ML/NLP venues, comprising 498/50/50 train/validation/test seed papers and approximately 7,600 cited references. Qwen2.5-7B-Instruct-1M is fine-tuned on a structured-text prompt that includes the citation graph, edge signals, reference information, and task definition to predict the idea for the seed paper. Across head-to-head LLM-judge tournaments against gpt-4o-driven baselines, GoR-SFT achieves SOTA, demonstrating the effectiveness of citation-evolution graphs as supervision signal for LLM-based idea generation. We hope that this reduces the barrier for citation evolution graphs as a supervision, accelerating automated scientific innovation.

Scientific progress depends on sequences of enabling contributions, yet existing AI4Science benchmarks largely focus on citation prediction, literature retrieval, or idea generation rather than the dependencies that make progress possible. In this paper, we introduce discovery pathway forecasting: given a target scientific contribution and the prior literature available at a specified time, the task is to (1) identify the enabling contributions required to realize it and (2) ground each in prior work when such prior work exists. We present SciPaths, a benchmark of 262 expert-annotated gold pathways and 2,444 silver pathways constructed from machine learning and natural language processing papers, where each pathway records enabling contributions, roles, rationales, and prior-work groundings or unmapped decisions. Evaluating frontier and open-weight language models, we find that the best model reaches only 0.189 F1 under strict semantic matching, with core methodological dependencies hardest to recover. Prior-work grounding improves substantially when gold enabling contributions are provided, showing that decomposition quality is a major bottleneck for end-to-end pathway recovery. SciPaths therefore shifts evaluation toward a missing capability in scientific forecasting: reasoning backward from a target contribution to the enabling scientific building blocks and prior-work dependencies that make it feasible.

Generative modeling has emerged as a promising approach for crystal structure discovery. However, existing LLM-based generative models struggle with low-level atomic precision, while diffusion-based methods fall short in integrating high-level scientific knowledge. As a result, generated structures are often invalid, unstable, or do not possess desirable properties. To address this gap, we propose CrystalReasoner (CrysReas), an end-to-end LLM framework that generates crystal structures from natural language instructions through reasoning and alignment. CrysReas introduces physical priors as thinking tokens, which include crystallographic symmetry, local coordination environments and predicted physical properties before generating atomic coordinates. This bridges the gap between natural language and 3D structures. CrysReas then employs reinforcement learning (RL) with a multi-objective, dense reward function to align generation with physical validity, chemical consistency, and thermodynamic stability. For property-conditioned tasks, we design task-specific reward functions and train specialized models for discrete constraints (e.g., space group) and continuous properties (e.g., elasticity, thermal expansion). Empirical results demonstrate that compared to prior works and baselines without thinking traces or RL, CrysReas obtains better performance on diverse metrics, triples S.U.N. ratio, and achieves better performance for property conditioned generation. CrysReas also exhibits adaptive reasoning, increasing reasoning lengths as the number of atoms increases. Our work demonstrates the potential of leveraging thinking traces and RL for generating valid, stable, and property-conditioned crystal structures.

AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm discovery. However, discovery success is shaped not only by model capability but also significantly by the design of the execution infrastructure, i.e., the harness. This paper investigates effective harness design through three questions: under a fixed token budget, is it better to produce many algorithms with brief thought or fewer algorithms with deeper thought? How should the harness handle evaluation hacks, where generated programs exploit the scoring function? And how can agents that require full filesystem access execute safely in parallel? Using Vesper, an algorithm discovery framework that incorporates harness improvements addressing these questions, we evaluate on Circle Packing under the same token budget. Interestingly, generating fewer algorithms while thinking more deeply about each one achieved higher scores. That is, scaling the quality of each individual is more budget-efficient than scaling the number of evolutionary generations. Surprisingly, more capable models produced evaluation hacks at higher rates, making hack detection increasingly necessary as models scale.

Large language models can extract local causal claims from text, but those claims become more useful when organized as persistent, navigable world models rather than as flat summaries. We introduce PROMETHEUS, a framework that turns retrieved literature, filings, reviews, reports, agent traces, source data, code, simulations, and scientific models into causal atlases: sheaf-like families of local causal predictive-state models over an explicit cover of a research substrate. Each local region contains causal episodes, structured claim tables, predictive tests, support statistics, and provenance; restriction maps compare overlapping regions; gluing diagnostics expose agreement, drift, contradiction, and underdetermination. The resulting Topos World Model is not a single universal graph. It is a research instrument for navigating what a corpus says, where it says it, how strongly it is supported, and where local claims fail to assemble into a coherent global view. Three literature-atlas case studies -- ocean-temperature impacts on marine populations, GLP-1 weight-loss evidence, and resveratrol/red-wine health-benefit claims -- illustrate deep causal research from text with explicit locality, evidence, persistent state, and gluing tension. Four grounded-counterfactual case studies -- a Nature Climate Change microplastics forcing paper, an Indus Valley hydrology paper with VIC-derived figure data and model code, the canonical Sachs protein-signaling study with single-cell perturbation data, and a Nature singing-mouse study with MAPseq projection matrices -- show a stronger mode: when a paper ships source data, simulation outputs, or code, PROMETHEUS can evaluate a counterfactual against that scientific substrate and then rebuild the sheaf world model around the

Cold-chain storage limits access to insulin for hundreds of millions of people; a thermally protective patch polymer could help, but the design space is too large for exhaustive experiment. Starting from that problem, we narrow to an agentic workflow: a large language model (LLM) calls physics-based tools through the Model Context Protocol (MCP), searching the discrete PSMILES space under a budget of OpenMM Packmol-matrix evaluations. The LLM acts as an implicit acquisition function conditioned on a persistent "discovery world": hypotheses, literature claims, and simulation outcomes updated each iteration. Under matched oracle budgets, the best autonomous campaign reaches an insulin-polymer interaction energy of -2263 kJ/mol, outperforming reinforcement-learning baselines by 68% and Bayesian optimization by 19%. Three independent campaigns converge on one structural motif (dense hydrogen-bond donors and acceptors per repeat unit) while physics checks reject infeasible packings and name-structure mismatches before they steer the next step. The science stage is CPU-bound and runs on commodity hardware. More broadly, the same architecture and workflow designed here applies to other protein-stabilization tasks whenever a tractable screening oracle is available.

The discovery of novel methodologies for emerging problems is a continuing cycle in ML, often driven by the migration of techniques across domains. Building on this observation, we ask whether current LLM ideation systems benefit from targeted cross-domain retrieval or simply from exposure to diverse mechanisms. We study this question through PaperGym, a three-stage pipeline: (1) tool-augmented seed extraction via read, grep, and bash over an isolated paper environment, (2) cross-domain seed retrieval via paraphrasing across seven ML domains, and (3) method synthesis from retrieved seeds, each scored by rubric-based judges. Tool-augmented extraction improves specificity, and paraphrase-based retrieval broadens domain coverage. In synthesis, cross-domain retrieval receives more pairwise novelty wins than no-retrieval and same-domain baselines, but shows no significant difference from a random diverse-seed control. These findings suggest LLM ideation systems benefit from diverse seed exposure, but do not yet reliably exploit the semantic reason particular seeds were retrieved. We release the seed library, rubric prompts, and run scripts at https://github.com/yunjoochoi/PaperGym

Scientific data processing often requires task-specific algorithms or AI models, creating a barrier for domain scientists who need to analyze their data but may not have extensive computing or image-processing expertise. This barrier is especially pronounced when data are noisy, have a high dynamic range, are sparsely labeled, or are only loosely specified. We introduce CVEvolve, an autonomous agentic harness with a zero-code interface for scientific data-processing algorithm discovery. CVEvolve combines a multi-round search strategy with tools for code execution, evaluation implementation, history management, holdout testing, and optional inspection of scientific data and visual outputs. The search alternates between discovery and improvement actions, and uses lineage-aware stochastic candidate sampling to balance exploration and exploitation. We demonstrate CVEvolve on X-ray fluorescence microscopy image registration, Bragg peak detection, high-energy diffraction microscopy image segmentation, and hybrid analytical-learning-based affine registration. Across these tasks, CVEvolve discovers algorithms that improve over baseline methods, while holdout test tracking helps identify candidates that generalize better than later over-optimized alternatives. These results show that zero-code, autonomous LLM-powered algorithm development can help domain scientists turn unstructured scientific image data into practical algorithms and downstream scientific discoveries.

Automated scientific discovery using large language models relies on identifying genuinely novel solutions. Standard reinforcement learning penalizes high-variance mutations, which leads the policy to prioritize familiar patterns. As a result, the maximum reward plateaus even as the average reward increases. Overcoming this limitation requires a signal that distinguishes unexplored regions from intrinsically difficult problems. This necessitates measuring disagreement across independently adapted weight hypotheses rather than relying on a single network's confidence. UG-TTT addresses this challenge by maintaining a small ensemble of low-rank adapters over a frozen base model. The per-token disagreement, quantified as the mutual information between ensemble predictions and weight hypotheses, isolates epistemic uncertainty and identifies positions where insufficient coverage leads to adapter divergence rather than intrinsic problem difficulty. This measure is incorporated as an exploration bonus into the policy gradient, directing the policy toward positions where persistent adapter disagreement signals low training coverage, the same frontier where genuine discovery is possible. A nuclear norm regularizer ensures the adapters remain distinct from one another, thereby preserving the exploration signal throughout training. Across four scientific discovery benchmarks, UG-TTT increases the maximum reward on three tasks, maintains substantially higher solution diversity, and an ablation study confirms that the regularizer is essential for sustaining this behavior.

Fast surrogate models for expensive simulations are now essential across the sciences, yet they typically operate as black boxes. We present \texttt{GWAgent}, a large language model (LLM)-based workflow that constructs interpretable analytic surrogates directly from simulation data. Surrogate modeling is well suited to agentic workflows because candidate models can be quantitatively validated against ground-truth simulations at each iteration. As a demonstration, we build a surrogate for gravitational waveforms from eccentric binary black hole mergers. We show that providing the agent with a physics-informed domain ansatz substantially improves output model accuracy. The resulting analytic surrogate attains a median Advanced LIGO mismatch of $6.9\times10^{-4}$ together with an $\sim 8.4\times$ speedup in waveform evaluation, surpassing both symbolic regression and conventional machine learning baselines. Beyond producing an accurate model, the workflow identifies compact physical structure from the learned representation. As an astrophysical application, we use \texttt{GWAgent} to analyze the eccentricity of GW200129 and infer $e_{20\mathrm{Hz}}=0.099^{+0.063}_{-0.044}$. These results show that validation-constrained agentic workflows can produce accurate, fast, and interpretable surrogates for scientific simulations and inference.

Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel and diverse solutions to open-ended problems. We evaluate LLMs on the task of open-ended solution generation and quantify their tendency to mode collapse into low-diversity generations. To mitigate this mode collapse, we introduce analogical reasoning (AR) as a new approach to solution generation. AR generates analogies to cross-domain problems based on shared relational structure, then uses those analogies to search for novel solutions. Compared to baselines, AR discovers significantly more diverse generations (improving solution diversity metrics by 90-173%), generates novel solutions over 50% of the time (compared to as little as 1.6% for baselines), and produces high-quality analogies. To validate the real-world feasibility of AR, we implement AR-generated solutions across four biomedical problems, yielding consistent quantitative gains. AR-generated approaches achieve a nearly 13-fold improvement on distributional metrics for perturbation effect prediction, outperform all baselines on AUPRC when predicting cell-cell communication, infer brain region interactions with a high Spearman correlation ($ρ$=0.729) to published methods, and establish state-of-the-art performance on 2 datasets for oligonucleotide property prediction. The novel and diverse solutions produced by AR can be used to augment the search space of existing solution generation methods.

As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing unevenly across tasks, domains, and model scales. In this work, we examine this dynamic jaggedness through the lens of scientific idea generation. We introduce SciAidanBench, a benchmark of open-ended scientific questions designed to measure the scientific creativity of large language models (LLMs). Given a scientific question, models are asked to generate as many unique and coherent ideas as possible, with the total number of valid responses serving as a proxy for creative potential. Evaluating 19 base models across 8 providers (30 total variants including reasoning versions), we find that jaggedness manifests both across models and within models. First, in a cross-task comparison between general and scientific creativity, improvements in general creativity do not translate uniformly to scientific creativity, revealing divergent capability profiles across models. Second, at the prompt level, stronger models do not improve uniformly; instead, they exhibit high variability, with bursts of creativity on some questions and limited performance on others. Third, at the domain level, individual models display uneven strengths across scientific subfields, reflecting fragmented internal capability profiles. Finally, we show that this jaggedness can be harnessed. We explore mechanisms of inference-time compute, knowledge pooling, and brainstorming to combine models effectively and construct meta-model ensembles that outperform any single model. Our results position jaggedness not as a limitation, but as a resource, a structural feature of AI progress that, when understood and leveraged, can amplify LLM-driven scientific creativity.

Current AI-powered research systems adopt a direct search-then-summarize paradigm that treats hypotheses as end products of scientific discovery. We argue this leaves a critical gap: hypotheses can serve a far more powerful role as organizational instruments that structure the research process itself. We propose the Hypothesis-Driven Deep Research (HDRI) methodology - the first framework using hypotheses to organize general-purpose deep research across arbitrary domains, rather than merely validating claims within specific domains. This transforms research from reactive information retrieval into proactive, verifiable, and iterative knowledge discovery. HDRI is formalized with six core principles and an eight-stage pipeline. A central innovation is the gap-driven iterative research mechanism - a closed-loop quality assurance system that automatically identifies informational and logical gaps, triggering targeted supplementary investigation. We further introduce a fact reasoning framework with traceable reasoning chains and quantified confidence propagation, a subject locking mechanism to prevent entity confusion, and a multi-dimensional quality assessment scheme. The methodology is realized in the INFOMINER system. Experiments demonstrate improvements of 22.4% in fact density, 90% subject matching accuracy, 0.92 multi-source verification confidence, and 14% completeness gain from gap-driven supplementation. Five case studies validate its practical applicability, achieving an average quality rating of 4.46/5.0.

Extracting multi-step explanations from knowledge graphs poses a combinatorial challenge requiring both heuristic guidance (as candidates proliferate with depth) and credit assignment (as path quality emerges over extended sequences). Frontier LLMs, strong on knowledge/reasoning benchmarks, offer a compelling source of such heuristics, yet their knowledge comes sans guarantees and compositional performance degrades as chains lengthen. We thus present TESSERA, a 3-part neuro-symbolic framework that uses LLMs in a circumscribed role: for local discriminative judgement rather than autonomous multi-step generation; the knowledge graph then defines the hypothesis space enforcing hard structural constraints, and MCTS coordinates the long-horizon search with principled credit assignment via backpropagation. LLMs perform dual roles as a prior policy biasing exploration and a comparative state evaluator supplying reward signals. Evaluation on drug mechanism elucidation across two complementary knowledge graphs demonstrates fidelity to curated biology while surfacing coherent alternative mechanisms, with ablations confirming discriminative contribution from both LLM components. Beyond its current application, our framework offers a general paradigm for compositional reasoning over structured knowledge.

A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery. We identify the following challenges in building and deploying autonomous AI scientists: (1) Problem selection is influenced by the McNamara fallacy; (2) Agents are built on large language models (LLMs) whose training corpora omit tacit procedural and failure knowledge of laboratory practice; (3) Preference optimisation during post-training compresses output diversity toward consensus; and (4) Most scientific benchmarks measure single-turn prediction accuracy and lack feedback from physical experiments back to the computational model. These challenges are not just questions of scale and scaffolding; they require revisiting fundamental design choices. To build truly autonomous AI scientists, we recommend the use of scientific simulations as verifiers for training, the design of persistent world models that represent the shifting objectives governing real investigations, the establishment of a centralized preregistration repository for all AI-generated hypotheses, and application driven by scientific need rather than tool affordance.

Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is increasingly important to understand whether they can discover such methods rather than only apply existing ones. We introduce MLS-Bench, a benchmark for evaluating whether AI systems can invent generalizable and scalable ML methods. MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings and scales. We find that current agents remain far from reliably surpassing human-designed methods, and that engineering-style tuning is easier for them than genuine method invention. We further study the effects of test-time scaling, adaptive compute allocation, and context provision on agents' discovery performance, together with case studies of their behavior. Our analyses suggest that the bottleneck is not only in proposing new methods, but also in the scientific insight needed to plan, validate, and scale claims about them. More search, compute, or context alone does not remove this bottleneck. We build and maintain a community platform for cumulative and comparable iteration, and release the data and code at https://mls-bench.com.

Balancing exploration and exploitation is a core challenge in sequential decision-making and black-box optimization. We introduce POETS ($\textbf{Po}$licy $\textbf{E}$nsembles for $\textbf{T}$hompson $\textbf{S}$ampling), a novel framework that bridges uncertainty quantification and policy optimization. Our approach is grounded in the insight that policies trained with Kullback-Leibler (KL) regularization implicitly encode an underlying reward function. Building on this, POETS bypasses the complex, nested process of training an uncertainty-aware reward model and separately fitting a policy to this model. Instead, we directly train a policy ensemble to capture epistemic uncertainty by matching implicitly encoded reward functions to online, bootstrapped data. To overcome the prohibitive compute and memory constraints of ensembling Large Language Models (LLMs), POETS utilizes an efficient architecture: the ensemble shares a pre-trained backbone while maintaining diversity through independent Low-Rank Adaptation (LoRA) branches. Theoretically, we prove that POETS implicitly conducts KL-regularized Thompson sampling and thus inherits strong cumulative regret bounds of ${\mathcal O}(\sqrt{T γ_T})$. Empirically, we demonstrate that POETS achieves state-of-the-art sample efficiency across diverse scientific discovery domains, including protein search and quantum circuit design. Furthermore, it improves the optimization trajectories of reinforcement learning, proving particularly robust in off-policy settings with experience replay or in small dataset regimes.

Cellular perturbation-response modeling requires coordinated choices of representations, fusion mechanisms, objectives, and training procedures. Large language models (LLMs) can propose executable candidates, but unconstrained revision can produce invalid implementations, change task semantics, or discard useful components. We present CellScientist, a protocol-constrained workflow that converts execution and validation feedback into auditable model-revision trajectories. It records design states and outcomes, routes discrepancies to specific components, and applies local revisions under a fixed task contract. A matched-budget study fixes the candidate language, predictor, fitting, and evaluator: structured revision finds better held-out predictors at small budgets under two LLM backbones. Operational audits link history to fewer repeated proposals, contract checks to contained violations, and discrepancy routing to targeted repairs. Refits of two frozen designs on an independently acquired cohort evaluate external predictive utility. Open-workflow trajectories retain improvements, regressions, and failures, while transcriptomic and single-cell searches extend application to additional response spaces. CellScientist produces both a selected predictor and an inspectable record of its development. Project page: https://limengran98.github.io/CellScientist/.

Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering ordinary differential equations with LLM-based qualitative and quantitative evaluation. DoLQ employs a multi-agent architecture: a Sampler Agent proposes dynamic system candidates, a Parameter Optimizer refines equations for accuracy, and a Scientist Agent leverages an LLM to conduct both qualitative and quantitative evaluations and synthesize their results to iteratively guide the search. Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations. Our code is available at https://github.com/Bon99yun/DoLQ.