SciAgent: Tool-augmented Language Models for Scientific Reasoning

A review of large language models and autonomous agents in chemistry

Ramos, M. C., Collison, C. J., & White, A. D. (2025) · Chemical Science · doi:10.1039/d4sc03921a · Cited by 274 · see citing works

Tool learning with large language models: a survey

Qu, C., Dai, S., Wei, X., Cai, H., Wang, S., Yin, D., Xu, J., & Wen, J.-R. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40678-2 · Cited by 261 · see citing works

AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges

Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 244 · see citing works

AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges

Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186 · see citing works

LLM Agents for Education: Advances and Applications

Chu, Z., Wang, S., Xie, J., Zhu, T., Yan, Y., Ye, J., Zhong, A., Hu, X., Liang, J., Yu, P. S., et al. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.743 · Cited by 96 · see citing works

A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective AgentsPreprint

Wei, T., Li, T.-W., Liu, Z., Ning, X., Yang, Z., Zou, J., Zeng, Z., Qiu, R., Lin, X., Fu, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.12538 · Cited by 94 · see citing works

LLM-Based Agents for Tool Learning: A Survey

Xu, W., Huang, C., Gao, S., & Shang, S. (2025) · Data Science and Engineering · doi:10.1007/s41019-025-00296-9 · Cited by 84 · see citing works

A Survey on Large Language Model BenchmarksPreprint

Ni, S., Chen, G., Li, S., Chen, X., Li, S., Wang, B., Wang, Q., Wang, X., Zhang, Y., Fan, L., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.15361 · Cited by 67 · see citing works

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning

Lin, Z., Gou, Z., Liang, T., Luo, R., Liu, H., & Yang, Y. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.91 · Cited by 41 · see citing works

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Zimmermann, Y., Bazgir, A., Al‐Feghali, A., Ansari, M., Bocarsly, J. D., Brinson, L. C., Chiang, Y., Çırcı, D., Chiu, M., Daelman, N., et al. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae011a · Cited by 32 · see citing works

CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool LearningPreprint

Wu, M., Wang, Y., Ming, Y., An, Y., Wan, Y., Chen, W., Lin, B., Li, Y., Xie, T., & Zhou, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.07551 · Cited by 32 · see citing works

Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize RiskPreprint

Chen, Z., Chen, J., Chen, J., & Sra, M. (2025) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2502.15865 · Cited by 29 · see citing works

Empowering Scientific Workflows with Federated Agents

Kamatar, A., Pauloski, J. G., Babuji, Y., Chard, R., Sakarvadia, M., Babnigg, D., Foster, I., & Chard, K. (2026) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps65963.2026.00114 · Cited by 27 · see citing works

ReCreate: Reasoning and Creating Domain Agents Driven by Experience

Hao, Z., Wang, H., Luo, J., Zhang, J., Zhou, Y., Lin, Q., Wang, C., Dong, H., & Chen, J. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.1432 · Cited by 27 · see citing works

MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science

Zhang, J., Gan, J., Wang, X., Jia, Z., Gu, C., Chen, J., Zhu, Y., Ma, M. D., Zhou, D., Li, L., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818888 · Cited by 26 · see citing works

Scientific Hypothesis Generation and Validation: Methods, Datasets, and Future DirectionsPreprint

Kulkarni, A., Alotaibi, F., Zeng, X., Wu, L., Zeng, T., Yao, B. M., Liu, M., Zhang, S., Huang, L., & Zhou, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.04651 · Cited by 25 · see citing works

Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and ChemistryPreprint

Zimmermann, Y., Bazgir, A., Afzal, Z., Agbere, F., Ai, Q., Alampara, N., Al‐Feghali, A., Ansari, M., Antypov, D., Aswad, A., et al. (2024) · arXiv (Cornell University) · doi:10.13016/m2bej2-ogic · Cited by 25 · see citing works

Evaluating and enhancing spatial cognition abilities of large language models

Yang, A., Fu, C., Jia, Q., Dong, W., Ma, M., Chen, H., Yang, F., & Wu, H. (2025) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2025.2490701 · Cited by 23 · see citing works

Agents of discovery

Diefenbacher, S., Hallin, A., Kasieczka, G., Krämer, M., Lauscher, A., & Lukas, T. (2026) · SciPost Physics · doi:10.21468/scipostphys.20.3.091 · Cited by 21 · see citing works

Toward Efficient Agents: Memory, Tool learning, and PlanningPreprint

Yang, X., Li, L., Zhou, H., Zhu, T., Qu, X., Fan, Y., Wei, Q., Ye, R., Kang, L., Qin, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.14192 · Cited by 18 · see citing works

Tool learning with language models: a comprehensive survey of methods, pipelines, and benchmarks

Chen, J., Wu, H., Pang, J., Wang, Y., Zhang, D., & Sun, C. (2025) · Vicinagearth. · doi:10.1007/s44336-025-00024-x · Cited by 15 · see citing works

Generalizable End-to-End Tool-Use RL with Synthetic CodeGymPreprint

Du, W., Gong, H., Ling, Z., Liu, K., Shen, L., Yao, X., Xu, Y., Shi, D., Yang, Y., & Chen, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.17325 · Cited by 15 · see citing works

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM AgentsPreprint

Shen, Y., Yang, Y., Xi, Z., Hu, B., Sha, H., Zhang, J., Peng, Q., Shang, J., Huang, J., Fan, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.12984 · Cited by 15 · see citing works

From large language models to AI agents in energy materials research: enabling discovery, design, and automation

Yao, T., Huang, J., Yan, Y., Yang, Y., Wang, Z., Shao, X., Gao, Z., & Yang, W. (2025) · AI Agent · doi:10.20517/aiagent.2025.03 · Cited by 14 · see citing works

Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills

Ding, M., Huang, C. J., Hu, Y., Li, Y., Lu, Z., Yu, X. H., Zhang, D., Zhai, W., Zhu, T., Gu, Q., et al. (2026) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.6c00622 · Cited by 10 · see citing works

Secure autonomous cyber defense with LLM agents: A systematic review of autonomy, tool-augmented reasoning, and governance constraints

Alqahtani, H., & Ahuja, P. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111184 · Cited by 9 · see citing works

MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems

Ye, X., Li, C., Chen, S., Wei, W., & Tang, R. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.755 · Cited by 9 · see citing works

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

Wei, J., Yang, Y., Zhang, X., Chen, Y., Zhuang, X., Gao, Z., Zhou, D., Wang, G., Gao, Z., Cao, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.14111 · Cited by 7 · see citing works

Agentic material science

Li, C., Ran, N., & Liu, J. (2026) · Journal of Materials Informatics · doi:10.20517/jmi.2025.87 · Cited by 7 · see citing works

RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step RetrievalPreprint

Oh, M., Kim, J., Lee, N., Seo, D., Kim, T., & Lee, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.08625 · Cited by 7 · see citing works

An agentic artificially intelligent X-ray scientist

Chen, Z., Petsch, A. N., Israelski, A., Plumley, R., Shen, L., Wang, C., Peng, C., Ni, Y., Bansil, A., Chowdhury, S., et al. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01261-5 · Cited by 6 · see citing works

Investigating Tool-Memory Conflicts in Tool-Augmented LLMsPreprint

Cheng, J., Pan, R., & Amiri, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.09760 · Cited by 6 · see citing works

FamilyTool: A Multi-hop Personalized Tool Use BenchmarkPreprint

Wang, Y., Guo, Y., Zheng, Y., Yin, Z., Chen, S., Yang, J., Chen, J., Li, Y., Huang, X., & Qiu, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.06766 · Cited by 5 · see citing works

Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems

Li, Y., Fu, X., Verma, G., Buitelaar, P., & Liu, M. (2025) · arXiv · doi:10.48550/arxiv.2510.24476 · Cited by 4 · see citing works

A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems

Ke, Z., Jiao, F., Ming, Y., Nguyen, X.-P., Xu, A., Long, D. X., Li, M., Qin, C., Wang, P., Savarese, S., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.09037 · Cited by 4 · see citing works

AI4Research: a survey of artificial intelligence for scientific research

Chen, Q., Yang, M., Qin, L., Liu, J., Yan, Z., Guan, J., Peng, D., Ji, Y., Li, H., Hu, M., et al. (2026) · Science China Information Sciences · doi:10.1007/s11432-025-5000-y · Cited by 4 · see citing works

Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM Reasoning

Ma, Z., Huang, Z., Liu, J., Wang, M.-X., Zhao, H., & Li, X. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i23.34664 · Cited by 4 · see citing works

MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level AssessmentPreprint

Ghahroodi, O., Hemmat, A., Nouri, M., Hosseini, S. M. H., Dastgheib, D., Sanian, M. V., Sahebi, A., Zohrabi, R., Rohban, M. H., Asgari, E., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.17290 · Cited by 4 · see citing works

Towards Autonomous and Auditable Medical Imaging Model DevelopmentPreprint

Liu, S., Jiang, J.-X., Zheng, B., Wang, C., Wang, Z., Pan, W., Wu, H., Peng, H., Gu, Y., Sun, L., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.10522 · Cited by 4 · see citing works

Large Language Model Reasoning Failures

Song, P., Han, P., & Goodman, N. (2026) · arXiv · doi:10.48550/arxiv.2602.06176 · Cited by 3 · see citing works

An Auditable Agent Platform For Automated Molecular Optimisation

Ünlü, A., Rohr, P., & Celebi, A. (2025) · arXiv · doi:10.48550/arxiv.2508.03444 · Cited by 3 · see citing works

Simulating Expert Discussions with Multi-agent for Enhanced Scientific Problem Solving

Li, Z., Yuan, C., & Le, X. (2024) · Workshop on Scholarly Document Processing (SDP) · doi:10.18653/v1/2024.sdp-1.23 · Cited by 3 · see citing works

Towards philosophical reasoning with agentic LLMs: Socratic method for scientific assistance

Harb, H., Sun, Y., Unal, M., Aggarwal, A., Bissolotti, C., Buyuker, I. S., Hong, S., Johnson, L. R., Jolaoso, L. A., Sengupta, B., et al. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae277f · Cited by 3 · see citing works

Analytical Search

Tu, Y. L., Miao, S., Su, W., Liu, Y., & Ai, Q. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3808536 · Cited by 3 · see citing works

Enhancing Tool Calling in LLMs with the International Tool Calling DatasetPreprint

Zhang, Z., & Zhu, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.05515 · Cited by 3 · see citing works

SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational SciencePreprint

Somasekharan, N., Hassan, Y., Lin, S., Panapitiya, G., Emami, P., Acharya, A., Horawalavithana, S., & Pan, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.18630 · Cited by 3 · see citing works

PDE-Agents: An LLM-Orchestrated Multi-Agent Framework for Automated Finite Element Simulations with Knowledge Graph-Augmented ReasoningPreprint

Adhikari, S., Noorsumar, G., & Jensen, Ø. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.07850 · Cited by 3 · see citing works

VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction

Yang, J., Chen, J., Yin, Z., Chen, S., Wang, Y., Guo, Y., Li, Y., Zheng, Y., Huang, X., & Qiu, X. (2025) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2025.findings-emnlp.23 · Cited by 2 · see citing works

From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent LLM Systems in Finance

Chen, Z., Chen, J., Chen, J., & Sra, M. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1934 · Cited by 2 · see citing works

Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and GeneralizationPreprint

Adams, C., Oliveira, R., Almeida, G., & Torres, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.19857 · Cited by 2 · see citing works

ChatMolData: A Multimodal Agent for Automatic Molecular Data Processing

Yu, Y., Wang, H., Zong, L., Chen, B., Li, Y., & Yu, X. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202401089 · Cited by 1 · see citing works

Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines

Kim, Y., Abdelaziz, A. A. A., Ferreira, T. C., Al-Badrashiny, M. A. S. A. A., & Sawaf, H. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-demo.32 · Cited by 1 · see citing works

Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval

Chen, J., Liu, G., He, S., Luo, K., Xu, Y., Zhao, J., & Liu, K. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.1356 · Cited by 1 · see citing works

BioR5: A Three-Layer Architecture for Biological Reasoning in Scientific AI

Ding, P., Brettin, T. S., & Stevens, R. L. (2025) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3731599.3767400 · Cited by 1 · see citing works

TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization

Jiang, M., Wang, Z., Wang, Q., Búš, P., Cheng, M., Wang, Y., Liu, Q., Li, R., Zeng, P., Liu, R., et al. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i44.41079 · Cited by 1 · see citing works

Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios

Xiao, X.-Y., Tian, Y., Yin, E., He, Z., Wang, S., Liu, Y., & Xia, Q. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.83 · Cited by 1 · see citing works

STEMVerse: A Dual-Axis Diagnostic Framework for STEM Reasoning in Large Language ModelsPreprint

Li, X., Li, X., Zhao, J., & Hu, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.02497 · Cited by 1 · see citing works

A Survey of Human-AI Collaboration for Scientific DiscoveryPreprint

Shi, C., Ren, X., Wang, Y., Li, J., Sun, Y., Luo, Y., & Sheng, R. (2026) · Preprints.org · doi:10.20944/preprints202601.0405.v2 · Cited by 1 · see citing works

FlowMind: Execute-Summarize for Structured Workflow Generation from LLM ReasoningPreprint

Liu, Y., Zhang, Z., He, Z., & Cai, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.11782 · Cited by 1 · see citing works

NNStar: An end-to-end AI agent for nuclear matter and neutron star physicsPreprint

Ma, Y., Ma, Y.-L., & Xiong, J.-Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.13930 · Cited by 1 · see citing works

EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural HazardsPreprint

Cui, Z., Yin, X., Tang, Y., Zhang, X., Hu, Y., Zhong, S., Tang, W., Liang, Y., Li, W., Jin, M., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.23525 · Cited by 1 · see citing works

Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents

Jaiswal, R., Jain, D., Popat, H. P., Anand, A., Dharmadhikari, A., Marathe, A., & Shah, R. R. (2024) · arXiv · doi:10.48550/arxiv.2412.00821

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning

Yue, M., Liu, Z., Yang, L., Zhang, J., Liu, Z., Chen, H., Yao, Z., Savarese, S., Xiong, C., Heinecke, S., et al. (2025) · arXiv · doi:10.48550/arxiv.2510.07768

Bel Esprit: Multi-Agent Framework for Building AI Model PipelinesPreprint

Kim, Y., Abdelaziz, A. A. A., Ferreira, T. C., Al-Badrashiny, M. A. S. A. A., & Sawaf, H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.14684

Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator

Liu, C., Wang, S., Qing, L., Lin, J., Zhang, J., Wu, F., & Kuang, K. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.245

CLINB: A Climate Intelligence Benchmark for Foundational ModelsPreprint

Huebscher, M. C., Mach, K. J., Stanić, A., Leippold, M., Gaiarin, B., Hausfather, Z., Rawat, E., Fischer, E. M., Ciaramita, M., Rogelj, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.11597

Co-BioBench and SDTL: Advancing Human-AI Collaboration in Open-Ended Scientific Discovery

Liu, Y., Wang, X., & Zhang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5764-6_24

Towards Trustworthy AI-Assisted Healthcare: Review on Studies Integrating LLMs, Multimodal Analysis, and Collaborative Filtering for Personalized Diagnosis

thri, S., & Sujith, A. V. L. N. (2026) · International Journal of Computer Science and Engineering · doi:10.14445/23488387/ijcse-v13i1p101

Grounded Chest X-Ray Reasoning: Leveraging Visual Tools to Improve Medical Multimodal LLMs

Wang, D. D., Xia, P., & Yao, H. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00391

The End of Trial-and-Error: A Vision for Generative Intelligence in Metamaterial Design

Kulkarni, A., Wang, H., Zhan, W., Chen, J., & Zhou, D. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00307

Infinite Problem Generator: Verifiably Scaling Physics Reasoning Data with Agentic WorkflowsPreprint

Sharan, A., Hebbale, S., & Kumar, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.14486

LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?

Exler, D., Raimann, M., Münker, M. F., Rosin, M., Gómez, J. E. U., Niemeyer, C. M., Reischl, M., & Rettenberger, L. (2026) · Advanced Intelligent Discovery · doi:10.1002/aidi.202500197

SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific DataPreprint

Liu, D., Qin, C., Chen, X., Li, X., Xu, W., Wang, Y., Chen, X., Zhou, Y., & Zhu, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.26645

Structure Liberates: How Constrained Sensemaking Produces More Novel Research OutputPreprint

Mooney, J., Kim, Z. M., Lee, Y.-J., & Kang, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.00557

PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving

Dong, Y., Zhang, X., Zhang, L., Lai, H., Li, P., Wei, B., Wu, Y., & Liu, J. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.458

ReflectCache: A Self-Reflective and Parameter-Level Caching Approach for Tool-Augmented Agents

Ma, J., Li, C., Li, X., Wang, C., Wang, Q., Zhang, Y., Yang, W., & Zhao, Z. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582719

S ci H orizon -D ata EVA: An Agentic System to Scalable AI-Readiness Evaluation of Heterogeneous Scientific Data

Liu, D., Qin, C., Chen, X., Li, X., Xu, W., Wang, Y., Chen, X., Zhou, Y., & Zhu, H. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818996

From Compression to Exploration: Active Querying Agent for 3D Physical Field Understanding

Gao, C., Zhou, H., Luo, Z., Jin, S., Yu, Q., Chen, T., & Li, J. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3819007

ChemEval2: A Diagnostic Benchmark for Evaluating Tool-Integrated Reasoning in Chemistry

Huang, Y., Tang, C., Liang, H., Fan, X., Wang, H., Xu, Y., Xia, Y., Jiang, W., Liu, D.-G., Xu, F., et al. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.190

SciBERT: A Pretrained Language Model for Scientific Text

Beltagy, I., Lo, K., & Cohan, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1371 · Cited by 3,218 · see citing works

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning

Yan, Y., Wang, S., Huo, J., Ye, J., Chu, Z., Hu, X., Yu, P. S., Gomes, C., Selman, B., & Wen, Q. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1228 · Cited by 16 · see citing works

AI Agents for Scientific Discovery Using Tool-Enhanced Reasoning

Azmat, H. (2026) · doi:10.13140/rg.2.2.31688.58881

PAPERMIND: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs

Zhao, Y., Wei, T., Zou, J., Ning, X., Bei, Y., Chen, L., Rana, S., Yang, W. H., Tong, H., & He, J. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.508 · Cited by 1 · see citing works

Vision and language foundation models in scientific reasoning

Burgess, J., Yeung, S. Y., Fox, E. B., Lundberg, E. K., Stanford University. School of Engineering., & Stanford University. Department of Computational and Mathematical Engineering. (2026) · Stanford Digital Repository · doi:10.25740/vs539ry1735