Scientific Reasoning in Language Models

Ask about this topic

Overview

The field studies whether language models can do more than recall scientific facts: interpret data, connect evidence, design tests, explain mechanisms, and generate useful hypotheses. Common approaches include chain-of-thought and structured reasoning traces, retrieval and tool use, multi-agent collaboration, and training with expert examples, simulators, or reinforcement learning with verifiable rewards. Evaluation spans scientific question answering, mathematics and physics problems, papers and tables, multimodal data, and interactive experimental workflows. Models are improving on specialized tasks, but reliable evidence use, robust execution, and mechanistic understanding remain difficult, and correct answers do not always show that a model reasoned scientifically.

Latest papers

CardsList

144 papers40 papers in the last four weeks, up 233% on the four weeks before. 0.2% of all new papers.

Apr 14, 2026

Evaluating Relational Reasoning in LLMs with REL

Relational reasoning is the ability to infer relations that jointly bind multiple entities, attributes, or variables. This ability is central to scientific reasoning, but existing evaluations of relational reasoning in large language models often focus on structured inputs such as tables, graphs, or synthetic tasks, and do not isolate the difficulty introduced by higher-arity relational binding. We study this problem through the lens of Relational Complexity (RC), which we define as the minimum number of independent entities or operands that must be simultaneously bound to apply a relation. RC provides a principled way to vary reasoning difficulty while controlling for confounders such as input size, vocabulary, and representational choices. Building on RC, we introduce REL, a generative benchmark framework spanning algebra, chemistry, and biology that varies RC within each domain. Across frontier LLMs, performance degrades consistently and monotonically as RC increases, even when the total number of entities is held fixed. This failure mode persists with increased test-time compute and in-context learning, suggesting a limitation tied to the arity of the required relational binding rather than to insufficient inference steps or lack of exposure to examples. Our results identify a regime of higher-arity reasoning in which current models struggle, and motivate re-examining benchmarks through the lens of relational complexity.

Lukas Fesser, Yasha Ektefaie, Ada Fang +2

Harvard University · Eric and Wendy Schmidt Center at the Broad Institute of MIT and Harvard

Relational ReasoningLLM EvaluationScientific Reasoning in Language Models
AskPDF
Apr 13, 2026

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators

We have witnessed remarkable advances in LLM reasoning capabilities with the advent of DeepSeek-R1. However, much of this progress has been fueled by the abundance of internet question-answer (QA) pairs, a major bottleneck going forward, since such data is limited in scale and concentrated mainly in domains like mathematics. In contrast, other sciences such as physics lack large-scale QA datasets to effectively train reasoning-capable models. In this work, we show that physics simulators can serve as a powerful alternative source of supervision for training LLMs for physical reasoning. We generate random scenes in physics engines, create synthetic question-answer pairs from simulated interactions, and train LLMs using reinforcement learning on this synthetic data. Our models exhibit zero-shot sim-to-real transfer to real-world physics benchmarks: for example, training solely on synthetic simulated data improves performance on IPhO (International Physics Olympiad) problems by 5-10 percentage points across model sizes. These results demonstrate that physics simulators can act as scalable data generators, enabling LLMs to acquire deep physical reasoning skills beyond the limitations of internet-scale QA data. Code available at: https://sim2reason.github.io/.

Mihir Prabhudesai, Aryan Satpathy, Yangmin Li +6

Carnegie Mellon University

Scientific Reasoning in Language ModelsSynthetic Data Generation for Language ModelsRL for Language Model Reasoning
AskPDF
Apr 13, 2026

Towards Autonomous Mechanistic Reasoning in Virtual Cells

Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their application in open-ended scientific domains such as biology remains limited, primarily due to the lack of factually grounded and actionable explanations. To address this, we introduce a structured explanation formalism for virtual cells that represents biological reasoning as mechanistic action graphs, enabling systematic verification and falsification. Building upon this, we propose VCR-Agent, a multi-agent framework that integrates biologically grounded knowledge retrieval with a verifier-based filtering approach to generate and validate mechanistic reasoning autonomously. Using this framework, we release VC-TRACES dataset, which consists of verified mechanistic explanations derived from the Tahoe-100M atlas. Empirically, we demonstrate that training with these explanations improves factual precision and provides a more effective supervision signal for downstream gene expression prediction. These results underscore the importance of reliable mechanistic reasoning for virtual cells, achieved through the synergy of multi-agent and rigorous verification.

Yunhui Jang, Lu Zhu, Jake Fawkes +3

Korea Advanced Institute of Science and Technology (KAIST) · Valence Labs · Recursion +1

Scientific Reasoning in Language ModelsMulti-Agent ReasoningGenomics
AskPDF
Apr 13, 2026

PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers

Leveraging Multi-modal Large Language Models (MLLMs) to accelerate frontier scientific research is promising, yet how to rigorously evaluate such systems remains unclear. Existing benchmarks mainly focus on single-document understanding, whereas real scientific workflows require integrating evidence from multiple papers, including their text, tables, and figures. As a result, multi-modal, multi-document scientific reasoning remains underexplored and lacks systematic evaluation. To address this gap, we introduce PaperScope, a multi-modal multi-document benchmark designed for agentic deep research. PaperScope presents three advantages: (1) Structured scientific grounding. It is built on a knowledge graph of over 2,000 AI papers spanning three years, providing a structured foundation for research-oriented queries. (2) Semantically dense evidence construction. It integrates semantically related key information nodes and employs optimized random-walk article selector to sample thematically coherent paper sets, thereby ensuring adequate semantic density and task complexity. (3) Multi-task evaluation of scientific reasoning. It contains over 2,000 QA pairs across reasoning, retrieval, summarization, and problem solving, enabling evaluation of multi-step scientific reasoning. Experimental results show that even advanced systems such as OpenAI Deep Research and Tongyi Deep Research achieve limited scores on PaperScope, highlighting the difficulty of long-context retrieval and deep multi-source reasoning. PaperScope thus provides a rigorous benchmark alongside a scalable pipeline for constructing large-scale multi-modal, multi-source deep research datasets.

Lei Xiong, Huaying Yuan, Zheng Liu +2

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · Beijing Academy of Artificial Intelligence, Beijing, China

AI Agent BenchmarksMultimodal Model EvaluationScientific Reasoning in Language ModelsMultimodal QA
AskPDF
Apr 13, 2026

When Verification Fails: How Compositionally Infeasible Claims Escape Rejection

Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries in evidence while preventing misinformation. This process involves evaluating each asserted constraint against validated evidence. Under the Closed-World Assumption (CWA), a claim is accepted if and only if all asserted constraints are positively supported. We show that existing verification benchmarks cannot distinguish models enforcing this standard from models applying a simpler shortcut called salient-constraint checking, which applies CWA's rejection criterion only to the most salient constraint and accepts when that constraint is supported. Because existing benchmarks construct infeasible claims by perturbing a single salient element they are insufficient at distinguishing between rigorous claim verification and simple salient-constraint reliance. To separate the two, we construct compositionally infeasible claims where the salient constraint is supported but a non-salient constraint is contradicted. Across model families and modalities, models that otherwise saturate existing benchmarks consistently over-accept these claims, confirming the prevalence of such shortcut reasoning. Via model context interventions, we show that different models and prompting strategies occupy distinct positions on a shared ROC curve, indicating that the gap between model families reflects differences in verification threshold rather than underlying reasoning ability, and that the compositional inference bottleneck is a structural property of current verification behavior that strategy guidance alone cannot overcome.

Muxin Liu, Delip Rao, Grace Kim +1

University of Pennsylvania

Scientific Claim VerificationScientific Reasoning in Language ModelsShortcut LearningCompositional Reasoning
AskPDF
Apr 12, 2026

SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?

Accelerating scientific discovery requires the identification of which experiments would yield the best outcomes before committing resources to costly physical validation. While existing benchmarks evaluate LLMs on scientific knowledge and reasoning, their ability to predict experimental outcomes - a task where AI could significantly exceed human capabilities - remains largely underexplored. We introduce SciPredict, a benchmark comprising 405 tasks derived from recent empirical studies in 33 specialized sub-fields of physics, biology, and chemistry. SciPredict addresses two critical questions: (a) can LLMs predict the outcome of scientific experiments with sufficient accuracy? and (b) can such predictions be reliably used in the scientific research process? Evaluations reveal fundamental limitations on both fronts. Model accuracies are 14-26% and human expert performance is ≈\approx20%. Although some frontier models exceed human performance model accuracy is still far below what would enable reliable experimental guidance. Even within the limited performance, models fail to distinguish reliable predictions from unreliable ones, achieving only ≈\approx20% accuracy regardless of their confidence or whether they judge outcomes as predictable without physical experimentation. Human experts, in contrast, demonstrate strong calibration: their accuracy increases from ≈\approx5% to ≈\approx80% as they deem outcomes more predictable without conducting the experiment. SciPredict establishes a rigorous framework demonstrating that superhuman performance in experimental science requires not just better predictions, but better awareness of prediction reliability. For reproducibility all our data and code are provided at https://github.com/scaleapi/scipredict

Udari Madhushani Sehwag, Elaine Lau, Haniyeh Ehsani Oskouie +14

Scale AI · University of California, Los Angeles · Human Frontier Collective, Scale AI +2

AI-Assisted Scientific ResearchScientific Reasoning in Language ModelsLLM ReliabilityLLM Uncertainty Estimation
AskPDF
Apr 10, 2026

Aryabhata 2: Scaling Reinforcement Learning for Advanced STEM Reasoning

Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understanding across physics, chemistry, and mathematics. Recent large language models perform strongly on common reasoning benchmarks, yet they remain difficult to deploy at scale, where millions of student doubts demand domain-specific, consistently structured problem solving. We introduce Aryabhata 2, a reasoning-focused language model for competitive STEM examinations, trained via reinforcement-learning post-training. Using PhysicsWallah's internal question banks, we construct a high-quality training curriculum and post-train GPT-OSS-20B through reinforcement learning with verifiable rewards. Training combines prolonged reinforcement learning with broadened exploration via progressively larger rollout group sizes. We evaluate Aryabhata 2 on competitive examination benchmarks, including JEE Main, JEE Advanced, and NEET, as well as out-of-distribution reasoning datasets such as AIME, HMMT, MMLU-Pro, MMLU-Redux 2.0, and GPQA. Results show that Aryabhata 2 outperforms its base model GPT-OSS-20B on competitive STEM reasoning while requiring substantially fewer output tokens (up to 64% fewer).

Ritvik Rastogi, Vishal Singh, Tejas Chaudhari +1

PhysicsWallah

Scientific Reasoning in Language ModelsEfficient Language Model ReasoningRL for Language Model Reasoning
AskPDF
Apr 8, 2026

Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs

Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination, hindering their practical application. Though scientific theories and rules can efficiently direct the behaviors of human manipulators, LLMs still do not utilize these highly-condensed knowledge sufficiently through training or prompting. To address this issue, we propose SciDC, an LLM generation method that integrate subject-specific knowledge with strong constraints. By adopting strong LLMs to automatically convert flexible knowledge into multi-layered, standardized rules, we build an extensible framework to effectively constrain the model generation on domain tasks. Experiments on scientific tasks including industrial formulation design, clinical tumor diagnosis and retrosynthesis planning, consistently demonstrate the effectiveness of our method, achieving a 12% accuracy improvement on average compared with vanilla generation. We further discuss the potential of LLMs in automatically inductively summarizing highly-condensed knowledge, looking ahead to practical solutions for accelerating the overall scientific research process. All the code of this paper can be obtained (https://github.com/Maotian-Ma/SciDC).

Maotian Ma, Zheni Zeng, Zhenghao Liu +1

Nanjing University · Tsinghua University · Northeastern University

LLM Hallucination MitigationKnowledge Augmentation for Language ModelsConstrained DecodingScientific Reasoning in Language Models
AskPDF
Apr 7, 2026

MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts

Large language models (LLMs) are widely explored for reasoning-intensive research tasks, yet resources for testing whether they can infer scientific conclusions from structured biomedical evidence remain limited. We introduce MedConclusion\textbf{MedConclusion}, a large-scale dataset of 5.7M\textbf{5.7M} PubMed structured abstracts for biomedical conclusion generation. Each instance pairs the non-conclusion sections of an abstract with the original author-written conclusion, providing naturally occurring supervision for evidence-to-conclusion reasoning. MedConclusion also includes journal-level metadata such as biomedical category and SJR, enabling subgroup analysis across biomedical domains. As an initial study, we evaluate diverse LLMs under conclusion and summary prompting settings and score outputs with both reference-based metrics and LLM-as-a-judge. We find that conclusion writing is behaviorally distinct from summary writing, strong models remain closely clustered under current automatic metrics, and judge identity can substantially shift absolute scores. MedConclusion provides a reusable data resource for studying scientific evidence-to-conclusion reasoning. Our code and data are available at: https://github.com/Harvard-AI-and-Robotics-Lab/MedConclusion.

Weiyue Li, Ruizhi Qian, Yi Li +5

Evidence-Grounded GenerationScientific Reasoning in Language Models
AskPDF
Apr 7, 2026

Can Large Language Models Reinvent Foundational Algorithms?

LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In this work, we focus on a prerequisite for foundational innovation: can LLMs reinvent foundational algorithms in computer science? We use LLM unlearning methods to suppress direct recall of the target algorithm and let the model reason with the remaining knowledge to recover it. Although unlearning does not guarantee full knowledge removal, LLMs fail to recover nearly half of the target algorithms. Notably, even suppressing the mention of the algorithm's name during decoding without unlearning makes the models' recovery rate drop dramatically (19--39%), suggesting their overreliance on memorized knowledge. We observe that recoverable algorithms tend to be simple in structure or core ideas, whereas the others are less straightforward. We also introduce a generative verifier that sustains models' reasoning strength, helping to avoid the ``thought collapse'' phenomenon. Taken together, by treating the unlearned model's recovery rate as an approximate upper bound, our empirical results suggest that current LLM systems still have limited ability to make foundational algorithm innovation. Our code is available at https://github.com/Algo-Reinvention/algo-reinvention.

Jian Zhao, Haoren Luo, Yu Wang +3

Xiongan AI Institute · Beijing University of Posts and Telecommunications, Beijing, China · Institute for Interdisciplinary Information Sciences, Tsinghua University +3

Algorithmic ReasoningScientific Reasoning in Language Models
AskPDF
Apr 6, 2026

Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether LMs can learn to forecast the empirical success of research ideas before any experiments are run. We study comparative empirical forecasting: given a benchmark-specific research goal and two candidate ideas, predict which will achieve better benchmark performance. We construct a dataset of 11,488 idea pairs grounded in objective outcomes from PapersWithCode. While off-the-shelf 8B-parameter models struggle (30% acc.), SFT dramatically boosts performance to 77.1%, outperforming GPT-5 (61.1%). By framing evaluation as a reasoning task via Reinforcement Learning with Verifiable Rewards (RLVR), we train models to discover latent reasoning paths, achieving 71.35% acc. with interpretable justifications. Through additional ablations and out-of-distribution tests, we show robustness to surface-level heuristics and transfer to both a cross-domain time-split test set and an independently constructed test set. Our results demonstrate that compute-efficient small language models can serve as effective, objective verifiers, offering a scalable path for autonomous scientific discovery.

Srujan P Mule, Aniketh Garikaparthi, Manasi Patwardhan

IISER Pune · TCS Research

Scientific Idea EvaluationLarge Language Model-Guided Scientific DiscoveryScientific Reasoning in Language Models
AskPDF
Apr 5, 2026

GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models

In many science papers, "Figure 1" serves as the primary visual summary of the core research idea. These figures are visually simple yet conceptually rich, often requiring significant effort and iteration by human authors to get right, highlighting the difficulty of science visual communication. With this intuition, we introduce GENFIG1, a benchmark for generative AI models (e.g., Vision-Language Models). GENFIG1 evaluates models for their ability to produce figures that clearly express and motivate the central idea of a paper (title, abstract, introduction, and figure caption) as input. Solving GENFIG1 requires more than producing visually appealing graphics: the task entails reasoning for text-to-image generation that couples scientific understanding with visual synthesis. Specifically, models must (i) comprehend and grasp the technical concepts of the paper, (ii) identify the most salient ones, and (iii) design a coherent and aesthetically effective graphic that conveys those concepts visually and is faithful to the input. We curate the benchmark from papers published at top deep-learning conferences, apply stringent quality control, and introduce an automatic evaluation metric that correlates well with expert human judgments. We evaluate a suite of representative models on GENFIG1 and demonstrate that the task presents significant challenges, even for the best-performing systems. We hope this benchmark serves as a foundation for future progress in multimodal AI.

Yaohan Guan, Pristina Wang, Najim Dehak +3

Johns Hopkins University

T2I Generation EvaluationVLM EvaluationScientific Reasoning in Language Models
AskPDF
Apr 4, 2026

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

Current multimodal benchmarks for scientific reasoning primarily evaluate local information extraction -- models recognize symbols and values and then perform textual inference. They do not assess whether models can reason over the global structural properties of formal diagrams, such as topology, conservation constraints, and the consistent mapping between visual patterns and algebraic expressions. We introduce FeynmanBench, a benchmark of over 2,000 tasks centered on Feynman diagrams spanning the electromagnetic, weak, and strong interactions of the Standard Model. Each instance couples a diagram image with minimal textual conventions and requires models to recover the full physical content -- vertex inventory, propagator types, topological connectivity, momentum routing, and the complete scattering amplitude. An automated generation and verification pipeline produces the diagrams, annotations, and reference answers under standardized rules. Evaluating 19 state-of-the-art multimodal LLMs, we find a consistent failure pattern: models achieve 70--95% on local recognition (vertex and propagator identification) but collapse to 13--17% on topological reconstruction (CP3), and near zero on full algebraic derivation (CP5). FeynmanBench offers a controlled testbed for multimodal reasoning over formal scientific diagrams and highlights fundamental limitations of current architectures in topology-sensitive scientific reasoning.

Zeyu Wang, Jingye Xu, Xiaogang Li +7

Alibaba Group, Beijing, China · Skylenage, Beijing, China

Scientific Reasoning in Language ModelsMultimodal ReasoningMultimodal Model Evaluation
AskPDF
Apr 3, 2026

BioAlchemy: Distilling Biological Literature into Reasoning-Ready Reinforcement Learning Training Data

Despite the large corpus of biology training text, the impact of reasoning models on biological research generally lags behind math and coding. In this work, we show that biology questions from current large-scale reasoning datasets do not align well with modern research topic distributions in biology, and that this topic imbalance may negatively affect performance. In addition, we find that methods for extracting challenging and verifiable research problems from biology research text are a critical yet underdeveloped ingredient in applying reinforcement learning for better performance on biology research tasks. We introduce BioAlchemy, a pipeline for sourcing a diverse set of verifiable question-and-answer pairs from a scientific corpus of biology research text. We curate BioAlchemy-345K, a training dataset containing over 345K scientific reasoning problems in biology. Then, we demonstrate how aligning our dataset to the topic distribution of modern scientific biology can be used with reinforcement learning to improve reasoning performance. Finally, we present BioAlchemist-8B, which improves over its base reasoning model by 9.12% on biology benchmarks. These results demonstrate the efficacy of our approach for developing stronger scientific reasoning capabilities in biology. The BioAlchemist-8B model is available at: https://huggingface.co/BioAlchemy.

Brian Hsu, Ozan Gökdemir, Carlo Siebenschuh +7

Department of Computer Science, University of Chicago, Chicago, IL 60637 · Data Science and Learning Division, Argonne National Laboratory, Lemont, IL 60439

Scientific Reasoning in Language ModelsScientific QARL for Language Model Reasoning
AskPDF
Apr 3, 2026

PolyReal: A Benchmark for Real-World Polymer Science Workflows

Multimodal Large Language Models (MLLMs) excel in general domains but struggle with complex, real-world science. We posit that polymer science, an interdisciplinary field spanning chemistry, physics, biology, and engineering, is an ideal high-stakes testbed due to its diverse multimodal data. Yet, existing benchmarks related to polymer science largely overlook real-world workflows, limiting their practical utility and failing to systematically evaluate MLLMs across the full, practice-grounded lifecycle of experimentation. We introduce PolyReal, a novel multimodal benchmark grounded in real-world scientific practices to evaluate MLLMs on the full lifecycle of polymer experimentation. It covers five critical capabilities: (1) foundational knowledge application; (2) lab safety analysis; (3) experiment mechanism reasoning; (4) raw data extraction; and (5) performance & application exploration. Our evaluation of leading MLLMs on PolyReal reveals a capability imbalance. While models perform well on knowledge-intensive reasoning (e.g., Experiment Mechanism Reasoning), they drop sharply on practice-based tasks (e.g., Lab Safety Analysis and Raw Data Extraction). This exposes a severe gap between abstract scientific knowledge and its practical, context-dependent application, showing that these real-world tasks remain challenging for MLLMs. Thus, PolyReal helps address this evaluation gap and provides a practical benchmark for assessing AI systems in real-world scientific workflows.

Wanhao Liu, Weida Wang, Jiaqing Xie +12

University of Science and Technology of China · Shanghai Artificial Intelligence Laboratory · Fudan University +5

Multimodal Model EvaluationMultimodal Large Language ModelsScientific Reasoning in Language ModelsMaterials Science
AskPDF
Apr 1, 2026

Grading the Unspoken: Evaluating Tacit Reasoning in Quantum Field Theory and String Theory with LLMs

Large language models have demonstrated impressive performance across many domains of mathematics and physics. One natural question is whether such models can support research in highly abstract theoretical fields such as quantum field theory and string theory. Evaluating this possibility faces an immediate challenge: correctness in these domains is layered, tacit, and fundamentally non-binary. Standard answer-matching metrics fail to capture whether intermediate conceptual steps are properly reconstructed or whether implicit structural constraints are respected. We construct a compact expert-curated dataset of twelve questions spanning core areas of quantum field theory and string theory, and introduce a five-level grading rubric separating statement correctness, key concept awareness, reasoning chain presence, tacit step reconstruction, and enrichment. Evaluating multiple contemporary LLMs, we observe near-ceiling performance on explicit derivations within stable conceptual frames, but systematic degradation when tasks require reconstruction of omitted reasoning steps or reorganization of representations under global consistency constraints. These failures are driven not only by missing intermediate steps, but by an instability in representation selection: models often fail to identify the correct conceptual framing required to resolve implicit tensions. We argue that highly abstract theoretical physics provides a uniquely sensitive lens on the epistemic limits of current evaluation paradigms.

Xingyang Yu, Yinghuan Zhang, Yufei Zhang +1

Department of physics, Virginia Tech · Independent Researcher · Department of Computer Science and Engineering, Michigan State University

Scientific Reasoning in Language ModelsLLM EvaluationImplicit Reasoning in Language ModelsReasoning Consistency in Language Models
AskPDF
Mar 30, 2026

CrossTrace: A Cross-Domain Dataset of Grounded Scientific Reasoning Traces for Hypothesis Generation

Scientific hypothesis generation is a critical bottleneck in accelerating research, yet existing datasets for training and evaluating hypothesis-generating models are limited to single domains and lack explicit reasoning traces connecting prior knowledge to novel contributions. I introduce CrossTrace, a dataset of 1,389 grounded scientific reasoning traces spanning biomedical research (518), AI/ML (605), and cross-domain work (266). Each trace captures the structured reasoning chain from established knowledge through intermediate logical steps to a novel hypothesis, with every step grounded in source paper text. I define an Input/Trace/Output schema that extends the Bit-Flip-Spark framework of HypoGen with step-level verification, a taxonomy of eight discovery patterns, and multi-domain coverage. Fine-tuning Qwen2.5-7B-Instruct on CrossTrace via QLoRA yields substantial improvements over the untuned baseline: IAScore rises from 0.828 to 0.968 (GPT-4o judge) and from 0.716 to 0.888 (Claude Opus 4.5), structural compliance improves from 0% to 100%, and spark cosine similarity increases from 0.221 to 0.620. Balanced cross-domain training (biomedical + AI/ML + CS) outperforms single-domain training, providing evidence that scientific reasoning patterns transfer across disciplines. Human validation of 150 stratified records confirms 99.7% step-level grounding accuracy and a 0.0% fabrication rate. To my knowledge, CrossTrace is the first large-scale, cross-domain dataset with step-level grounded reasoning traces for hypothesis generation, and my results demonstrate that such traces are an effective training signal whose benefits are at least partially domain-general.

Andrew Bouras, OMS-II Research Fellow

Nova Southeastern University Dr. Kiran C. Patel College of Osteopathic Medicine Clearwater, FL 33760, USA

Scientific Hypothesis GenerationScientific Reasoning in Language ModelsScientific ReasoningEvidence-Grounded GenerationCross-Domain Generalization
AskPDF
Mar 30, 2026

Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners

As Large Language Models (LLMs) achieve increasingly sophisticated performance on complex reasoning tasks, current architectures serve as critical proxies for the internal heuristics of frontier models. Characterizing emergent reasoning is vital for long-term interpretability and safety. Furthermore, understanding how prompting modulates these processes is essential, as natural language will likely be the primary interface for interacting with AGI systems. In this work, we use a custom variant of Genetic Pareto (GEPA) to systematically optimize prompts for scientific reasoning tasks, and analyze how prompting can affect reasoning behavior. We investigate the structural patterns and logical heuristics inherent in GEPA-optimized prompts, and evaluate their transferability and brittleness. Our findings reveal that gains in scientific reasoning often correspond to model-specific heuristics that fail to generalize across systems, which we call "local" logic. By framing prompt optimization as a tool for model interpretability, we argue that mapping these preferred reasoning structures for LLMs is an important prerequisite for effectively collaborating with superhuman intelligence.

Rohan Pandey, Eric Ye, Michael Li

Carnegie Mellon University

LLM PromptingLLM InterpretabilityScientific Reasoning in Language ModelsPrompt OptimizationPrompt Robustness
AskPDF
Mar 29, 2026

PRBench: End-to-end Paper Reproduction in Physics Research

AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation and code generation. However, whether these agents can reliably perform end-to-end reproduction from real scientific papers remains an open question. We introduce PRBench, a benchmark of 30 expert-curated tasks spanning 11 subfields of physics. Each task requires an agent to comprehend the methodology of a published paper, implement the corresponding algorithms from scratch, and produce quantitative results matching the original publication. Agents are provided only with the task instruction and paper content, and operate in a sandboxed execution environment. All tasks are contributed by domain experts from over 20 research groups at the School of Physics, Peking University, each grounded in a real published paper and validated through end-to-end reproduction with verified ground-truth results and detailed scoring rubrics. Using an agentified assessment pipeline, we evaluate a set of coding agents on PRBench and analyze their capabilities across key dimensions of scientific reasoning and execution. The best-performing agent, OpenAI Codex powered by GPT-5.3-Codex, achieves a mean overall score of 34%. All agents exhibit a zero end-to-end callback success rate, with particularly poor performance in data accuracy and code correctness. We further identify systematic failure modes, including errors in formula implementation, inability to debug numerical simulations, and fabrication of output data. Overall, PRBench provides a rigorous benchmark for evaluating progress toward autonomous scientific research.

Shi Qiu, Junyi Deng, Yiwei Deng +48

AI Agent BenchmarksAI Coding AgentsScientific ReproducibilityScientific Reasoning in Language Models
AskPDF
Mar 27, 2026

Are LLMs Good For Quantum Software, Architecture, and System Design?

Quantum computers promise massive computational speedup for problems in many critical domains, such as physics, chemistry, cryptanalysis, healthcare, etc. However, despite decades of research, they remain far from entering an era of utility. The lack of mature software, architecture, and systems solutions capable of translating quantum-mechanical properties of algorithms into physical state transformations on qubit devices remains a key factor underlying the slow pace of technological progress. The problem worsens due to significant reliance on domain-specific expertise, especially for software developers, computer architects, and systems engineers. To address these limitations and accelerate large-scale high-performance quantum system design, we ask: Can large language models (LLMs) help with solving quantum software, architecture, and systems problems? In this work, we present a case study assessing the performance of LLMs on quantum system reasoning tasks. We evaluate nine frontier LLMs and compare their performance to graduate UT Austin students on a set of quantum computing problems. Finally, we recommend several directions along which research and engineering development efforts must be pursued.

Sourish Wawdhane, Poulami Das

The University of Texas at Austin

LLM EvaluationScientific Reasoning in Language Models
AskPDF
Mar 27, 2026

Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

With the rapid progress of multimodal large language models (MLLMs), AI already performs well at literature retrieval and certain reasoning tasks, serving as a capable assistant to human researchers, yet it remains far from autonomous research. The fundamental reason is that current work on academic paper reasoning is largely confined to a search-oriented paradigm centered on pre-specified targets, with reasoning grounded in relevance retrieval, which struggles to support researcher-style full-document understanding, reasoning, and verification. To bridge this gap, we propose ScholScan, a new benchmark for academic paper reasoning. ScholScan introduces a scan-oriented task setting that asks models to read and cross-check entire papers like human researchers, scanning the document to identify consistency issues. The benchmark comprises 1,800 carefully annotated questions drawn from nine error categories across 13 natural-science domains and 715 papers, and provides detailed annotations for evidence localization and reasoning traces, together with a unified evaluation protocol. We assessed 15 models across 24 input configurations and conducted a fine-grained analysis of MLLM capabilities for all error categories. Across the board, retrieval-augmented generation (RAG) methods yield no significant improvements, revealing systematic deficiencies of current MLLMs on scan-oriented tasks and underscoring the challenge posed by ScholScan. We expect ScholScan to be the leading and representative work of the scan-oriented task paradigm.

Rongjin Li, Zichen Tang, Xianghe Wang +9

Beijing University of Posts and Telecommunications

LLM EvaluationScientific Reasoning in Language ModelsMultimodal Reasoning
AskPDF
Mar 26, 2026

MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation

Large language models (LLMs) hold considerable potential for advancing scientific discovery, yet systematic assessment of their dynamic reasoning in real-world research remains limited. Current scientific evaluation benchmarks predominantly rely on static, single-turn Question Answering (QA) formats, which are inadequate for measuring model performance in complex scientific tasks that require multi-step iteration and experimental interaction. To address this gap, we introduce MolQuest, a novel agent-based evaluation framework for molecular structure elucidation built upon authentic chemical experimental data. Unlike existing datasets, MolQuest formalizes molecular structure elucidation as a multi-turn interactive task, requiring models to proactively plan experimental steps, integrate heterogeneous spectral sources (e.g., NMR, MS), and iteratively refine structural hypotheses. This framework systematically evaluates LLMs' abductive reasoning and strategic decision-making abilities within a vast and complex chemical space. Empirical results reveal that contemporary frontier models exhibit significant limitations in authentic scientific scenarios: notably, even state-of-the-art (SOTA) models achieve an accuracy of only approximately 50%, while the performance of most other models remains below the 30% threshold. This work provides a reproducible and extensible framework for science-oriented LLM evaluation, our findings highlight the critical gap in current LLMs' strategic scientific reasoning, setting a clear direction for future research toward AI that can actively participate in the scientific process.

Taolin Han, Shuang Wu, Jinghang Wang +4

Alibaba Group, Hangzhou, China

Abductive Reasoning in Language ModelsScientific Reasoning in Language ModelsAI Agent BenchmarksAI Agent Evaluation
AskPDF
Mar 26, 2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.

Yicheng Zou, Dongsheng Zhu, Lin Zhu +174

Multimodal Foundation ModelsAI for ScienceScientific Reasoning in Language ModelsLanguage Model Scaling
AskPDF
Mar 25, 2026

ThermoQA: A Three-Tier Benchmark for Evaluating Thermodynamic Reasoning in Large Language Models

We present ThermoQA, a benchmark of 293 open-ended engineering thermodynamics problems in three tiers: property lookups (110 Q), component analysis (101 Q), and full cycle analysis (82 Q). Ground truth is computed programmatically from CoolProp 7.2.0, covering water, R-134a, and variable-cp air. Six frontier LLMs are evaluated across three independent runs each. The composite leaderboard is led by Claude Opus 4.6 (94.1%), GPT-5.4 (93.1%), and Gemini 3.1 Pro (92.5%). Cross-tier degradation ranges from 2.8 pp (Opus) to 32.5 pp (MiniMax), confirming that property memorization does not imply thermodynamic reasoning. Supercritical water, R-134a refrigerant, and combined-cycle gas turbine analysis serve as natural discriminators with 40-60 pp performance spreads. Multi-run sigma ranges from +/-0.1% to +/-2.5%, quantifying reasoning consistency as a distinct evaluation axis. Dataset and code are open-source at https://huggingface.co/datasets/olivenet/thermoqa

Kemal Düzkar

Olivenet Kyrenia, Cyprus

LLM EvaluationScientific Reasoning in Language ModelsNumerical Reasoning in Language ModelsReasoning Consistency in Language Models
AskPDF
Mar 23, 2026

Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning

LLMs often generate seemingly valid answers to flawed or ill-posed inputs. This is not due to missing knowledge: under discriminative prompting, the same models can mostly identify such issues, yet fail to reflect this in standard generative responses. This reveals a fundamental know-act gap between discriminative recognition and generative behavior. Prior work largely characterizes this issue in narrow settings, such as math word problems or question answering, with limited focus on how to integrate these two modes. In this work, we present a comprehensive analysis using FaultyScience, a newly constructed large-scale, cross-disciplinary benchmark of faulty scientific questions. We show that the gap is pervasive and stems from token-level autoregression, which entangles task selection (validate vs. answer) with content generation, preventing discriminative knowledge from being utilized. To address this, we propose DeIllusionLLM, a task-level autoregressive framework that explicitly models this decision. Through self-distillation, the model unifies discriminative judgment and generative reasoning within a single backbone. Empirically, DeIllusionLLM substantially reduces answer-despite-error failures under natural prompting while maintaining general reasoning performance, demonstrating that self-distillation is an effective and scalable solution for bridging the discriminative-generative know-act gap

Jihyun Janice Ahn, Ryo Kamoi, Berk Atil +34

Penn State · UIUC · Columbia University +1

Scientific Reasoning in Language Models
AskPDF
Mar 20, 2026

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational approaches are misaligned with this reality, framing discovery as isolated, task-specific predictions rather than continuous interaction with the physical world. Here, we argue for embodied science, a paradigm that reframes scientific discovery as a closed loop tightly coupling agentic reasoning with physical execution. We propose a unified Perception-Language-Action-Discovery (PLAD) framework, wherein embodied agents perceive experimental environments, reason over scientific knowledge, execute physical interventions, and internalize outcomes to drive subsequent exploration. By grounding computational reasoning in robust physical feedback, this approach bridges the gap between digital prediction and empirical validation, offering a roadmap for autonomous discovery systems in the life and chemical sciences.

Xiang Zhuang, Chenyi Zhou, Kehua Feng +10

Zhejiang University, Hangzhou, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · Tongji University, Shanghai, China

AI Agents for Scientific DiscoveryAutonomous ExperimentationEmbodied AIScientific Reasoning in Language Models
AskPDF
Mar 19, 2026

MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models

Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoning, resulting in surface-level conceptual recombinations that lack technical depth and scientific grounding. To address this issue, we propose MoRI (Motivation-grounded Reasoning for Scientific Ideation), a framework that enables LLMs to explicitly learn the reasoning process from research motivations to methodologies. The base LLM is initialized via supervised fine-tuning to generate a research motivation from a given context, and is subsequently trained under a composite reinforcement learning reward that approximates scientific rigor: (1) entropy-aware information gain encourages the model to uncover and elaborate high-complexity technical details grounded in ground-truth methodologies, and (2) contrastive semantic gain constrains the reasoning trajectory to remain conceptually aligned with scientifically valid solutions. Empirical results show that MoRI consistently outperforms strong commercial LLMs and complex agentic baselines across multiple dimensions, including novelty, technical rigor, and feasibility. The code is available on GitHub.

Chenyang Gu, Jiahao Cheng, Meicong Zhang +3

School of Economics and Management, East China Normal University

Scientific Reasoning in Language ModelsLarge Language Model-Guided Scientific DiscoveryScientific Hypothesis GenerationRL for Language Model Reasoning
AskPDF
Mar 19, 2026

Mathematical Reasoning Enhanced LLM for Formula Derivation: A Case Study on Fiber NLI Modellin

Recent advances in large language models (LLMs) have demonstrated strong capabilities in code generation and text synthesis, yet their potential for symbolic physical reasoning in domain-specific scientific problems remains underexplored. We present a mathematical reasoning enhanced generative AI approach for optical communication formula derivation, focusing on the fiber nonlinear interference modelling. By guiding an LLM with structured prompts, we successfully reconstructed the known closed-form ISRS GN expressions and further derived a novel approximation tailored for multi-span C and C+L band transmissions. Numerical validations show that the LLM-derived model produces central-channel GSNRs nearly identical to baseline models, with mean absolute error across all channels and spans below 0.109 dB, demonstrating both physical consistency and practical accuracy.

Yao Zhang, Yuchen Song, Xiao Luo +4

State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, China

Scientific Reasoning in Language ModelsLLM Mathematical Reasoning
AskPDF
Mar 17, 2026

PRISM: Demystifying Retention and Interaction in Mid-Training

We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two architecture types (dense Transformer and attention-Mamba hybrid), and scales from 3B to 24B parameters, we show that mid-training on approximately 27B high-quality tokens yields consistent gains of +15 to +40 points on math, +5 to +12 points on code, and +6 to +13 points on science benchmarks while preserving general performance. The full PRISM to RL pipeline improves macro-average across six reasoning benchmarks from under 12 to 29-42 (a 3-4x improvement), whereas RL applied directly to most of the base models remains substantially less effective, with AIME scores near zero. Data composition matters most at mid-training, not RL: including science data during mid-training unlocks +17 to +28 point GPQA-Diamond gains during RL, while changing the RL mix produces less than 2 point differences. Mechanistically, mid-training densely restructures over 90% of model weights, while RL makes sparse, front-loaded refinements to approximately 5% of parameters. Representation analysis (CKA) confirms that RL consistently preserves mid-training's representational geometry (over 0.998 CKA) across architectures. Crucially, RL applies identical weight changes regardless of starting point, yet only succeeds on mid-trained models, consistent with mid-training placing the model in a configuration from which RL can effectively improve performance. Our results demonstrate that retention-aware mid-training is highly effective for reliable reasoning enhancement and provide practical guidance for designing robust mid-training pipelines.

Bharat Runwal, Ashish Agrawal, Anurag Roy +1

IBM Research, MIT-IBM Watson AI Lab

LLM TrainingScientific Reasoning in Language ModelsRL for Language Model Reasoning
AskPDF
Mar 16, 2026

OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning

Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous spatiotemporal dynamics governed by Partial Differential Equations (PDEs), often resulting in non-physical hallucinations. Existing approaches typically resort to costly, domain-specific fine-tuning, which severely limits cross-domain generalization and interpretability. To bridge this gap, we propose OMNIFLOW, a neuro-symbolic architecture designed to ground frozen multimodal LLMs in fundamental physical laws without requiring domain-specific parameter updates. OMNIFLOW introduces a novel Semantic-Symbolic Alignment mechanism that projects high-dimensional flow tensors into topological linguistic descriptors, enabling the model to perceive physical structures rather than raw pixel values. Furthermore, we construct a Physics-Guided Chain-of-Thought (PG-CoT) workflow that orchestrates reasoning through dynamic constraint injection (e.g., mass conservation) and iterative reflexive verification. We evaluate OMNIFLOW on a comprehensive benchmark spanning microscopic turbulence, theoretical Navier-Stokes equations, and macroscopic global weather forecasting. Empirical results demonstrate that OMNIFLOW significantly outperforms traditional deep learning baselines in zero-shot generalization and few-shot adaptation tasks. Crucially, it offers transparent, physically consistent reasoning reports, marking a paradigm shift from black-box fitting to interpretable scientific reasoning.

Hao Wu, Yongheng Zhang, Yuan Gao +7

Tsinghua University · Tencent · Shenzhen Loop Area Institute +2

Scientific Reasoning in Language ModelsPhysics-Informed MLPDE SolvingMultimodal Reasoning
AskPDF