ScienceWorld: Is your Agent Smarter than a 5th Grader?
Open accessAbstract
We present SCIENCEWORLD, a benchmark to test agents' scientific reasoning abilities in a new interactive text environment at the level of a standard elementary school science curriculum.Despite the transformer-based progress seen in question-answering and scientific text processing, we find that current models cannot reason about or explain learned science concepts in novel contexts.For instance, models can easily answer what the conductivity of a known material is but struggle when asked how they would conduct an experiment in a grounded environment to find the conductivity of an unknown material.This begs the question of whether current models are simply retrieving answers by way of seeing a large number of similar examples or if they have learned to reason about concepts in a reusable manner.We hypothesize that agents need to be grounded in interactive environments to achieve such reasoning capabilities.Our experiments provide empirical evidence supporting this hypothesisshowing that a 1.5 million parameter agent trained interactively for 100k steps outperforms a 11 billion parameter model statically trained for scientific question-answering and reasoning from millions of expert demonstrations.12
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
SciWorld is suitable for testing an agent's ability to retain and retrieve relevant knowledge over extended interaction sequences.
“Its complexity makes it suitable for testing an agent's ability to retain and retrieve relevant knowledge over extended interaction sequences.”
From Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents (2026) · cites this paper as Wang et al., 2022
Section 3 describes ScienceWorld as a complex interactive environment, and the Abstract says agents must combine scientific knowledge with sequences of actions to complete experiments. The Learning Agents section also describes a task solvable by retrieving a critical answer. These passages support testing knowledge use during interaction, but do not establish that the benchmark specifically tests retaining and retrieving knowledge over extended sequences. (LLM, conf=0.82)
Experimental — accuracy not yet measuredSequential and interactive environments such as ScienceWorld, ALFWorld, TextWorld, and Jericho, along with programming benchmarks like APPS, SWE-bench, SWE-Bench Pro, and SWE-Lancer, increase task complexity but remain episodic, reset-centric, and evaluation-driven.
“Sequential and interactive environments such as ScienceWorld (Wang et al., 2022), ALFWorld (Shridhar et al., 2021), TextWorld (Côté et al., 2018), and Jericho (Hausknecht et al., 2020), along with programming benchmarks like APPS (Hendrycks et al., 2021a), SWE-bench (Jimenez et al., 2024), SWE-Bench Pro (Deng et al., 2025), and SWE-Lancer (Miserendino et al., 2025), increase task complexity but”
From A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents (2026) · cites this paper as Wang et al., 2022
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 33
- Prithviraj Ammanabrolu, Renee Jia, and Mark O Riedl. 2022. Situated dialogue learning through procedural environment generation. In Association for Compu- tational Linguistics (ACL) 2022.
- Prithviraj Ammanabrolu, Ethan Tien, Matthew Hausknecht, and Mark O Riedl. 2020. How to avoid being eaten by a grue: Structured explo- ration strategies for textual worlds. arXiv preprint arXiv:2006.07409. · arXiv
- Prithviraj Ammanabrolu, Jack Urbanek, Margaret Li, Arthur Szlam, Tim Rocktäschel, and Jason Weston. 2021. How to motivate your dragon: Teaching goal- driven agents to speak and act in fantasy worlds. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, pages 807-833, Online. Association for Computa- tional Linguistics. · DOI
- Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Mu- rugesan, and Mrinmaya Sachan. 2021. Case-based reasoning for better generalization in text-adventure games. In Proceedings of the International Confer- ence on Learning Representations.
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Ad- vances in Neural Information Processing Systems, volume 33, pages 1877-1901.
- Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Ar- avind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. arXiv preprint arXiv:2106.01345. · arXiv
- Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. Think you have solved question an- swering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457. · arXiv
- Peter Clark, Oren Etzioni, Tushar Khot, Daniel Khashabi, Bhavana Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Niket Tandon, et al. 2020. From 'f'to 'a'on the ny regents science exams: An overview of the aristo project. AI Magazine, 41(4):39-53.
- Marc-Alexandre Côté, Ákos Kádár, Xingdi Yuan, Ben Kybartas, Tavian Barnes, Emery Fine, James Moore, Matthew Hausknecht, Layla El Asri, Mahmoud Adada, et al. 2018. Textworld: A learning environ- ment for text-based games. In Workshop on Com- puter Games, pages 41-75. Springer.
- Leilani H Gilpin, David Bau, Ben Z Yuan, Ayesha Ba- jwa, Michael Specter, and Lalana Kagal. 2018. Ex- plaining explanations: An overview of interpretabil- ity of machine learning. In 2018 IEEE 5th Inter- national Conference on data science and advanced analytics (DSAA), pages 80-89. IEEE.
- Matthew Hausknecht, Prithviraj Ammanabrolu, Marc- Alexandre Côté, and Xingdi Yuan. 2020. Interactive fiction games: A colossal adventure. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 7903-7910.
- Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022. Language models as zero-shot planners: Extracting actionable knowledge for em- bodied agents. arXiv preprint arXiv:2201.07207. Infocom. 1989. Learning zil. · arXiv
- Peter Jansen, Niranjan Balasubramanian, Mihai Sur- deanu, and Peter Clark. 2016. What's in an expla- nation? characterizing knowledge and inference re- quirements for elementary science exams. In Pro- ceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2956-2965, Osaka, Japan. The COL- ING 2016 Organizing Committee.
- Peter Jansen, Elizabeth Wainwright, Steven Mar- morstein, and Clayton Morrison. 2018. WorldTree: A corpus of explanation graphs for elementary sci- ence questions supporting multi-hop inference. In Proceedings of the Eleventh International Confer- ence on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Re- sources Association (ELRA).
- Peter A Jansen. 2021. A systematic survey of text worlds as embodied natural language environments. arXiv preprint arXiv:2107.04132. · arXiv
- Tushar Khot, Peter Clark, Michal Guerquin, Peter Jansen, and Ashish Sabharwal. 2020. Qasc: A dataset for question answering via sentence compo- sition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 8082-8090.
- P David Lebling, Marc S Blank, and Timothy A Ander- son. 1979. Zork: a computerized fantasy simulation game. Computer, 12(04):51-59.
- Tania Lombrozo. 2006. The structure and function of ex- planations. Trends in cognitive sciences, 10(10):464- 470.
- Chris Martens. 2015. Ceptre: A language for modeling generative interactive systems. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, volume 11.
- Keerthiram Murugesan, Mattia Atzeni, Pavan Ka- panipathi, Pushkar Shukla, Sadhana Kumaravel, Gerald Tesauro, Kartik Talamadupula, Mrinmaya Sachan, and Murray Campbell. 2020a. Text-based rl agents with commonsense knowledge: New chal- lenges, environments and baselines. arXiv preprint arXiv:2010.03790. · arXiv
- Keerthiram Murugesan, Mattia Atzeni, Pushkar Shukla, Mrinmaya Sachan, Pavan Kapanipathi, and Kartik Ta- lamadupula. 2020b. Enhancing text-based reinforce- ment learning agents with commonsense knowledge. arXiv preprint arXiv:2005.00811. · arXiv
- Xiangyu Peng, Mark O Riedl, and Prithviraj Am- manabrolu. 2021. Inherently explainable reinforce- ment learning in natural language. arXiv preprint arXiv:2112.08907. · arXiv
- Colin Raffel, Noam Shazeer, Adam Roberts, Kather- ine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1-67.
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. " why should i trust you?" explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135- 1144.
- Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2020. Alfworld: Aligning text and em- bodied environments for interactive learning. arXiv preprint arXiv:2010.03768. · arXiv
- Oyvind Tafjord and Peter Clark. 2021. General-purpose question-answering with Macaw. arXiv preprint arXiv:2106.01345. · arXiv
- Ronen Tamari, Fan Bai, Alan Ritter, and Gabriel Stanovsky. 2021. Process-level representation of scientific protocols with interactive annotation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Lin- guistics: Main Volume, pages 2190-2202, Online. Association for Computational Linguistics. · DOI
- Zhengnan Xie, Sebastian Thiem, Jaycie Martin, Eliz- abeth Wainwright, Steven Marmorstein, and Peter Jansen. 2020. WorldTree v2: A corpus of science- domain structured explanations and inference pat- terns supporting multi-hop inference. In Proceedings of the 12th Language Resources and Evaluation Con- ference, pages 5456-5473, Marseille, France. Euro- pean Language Resources Association.
- Dongfang Xu, Peter Jansen, Jaycie Martin, Zhengnan Xie, Vikas Yadav, Harish Tayyar Madabushi, Oyvind Tafjord, and Peter Clark. 2020. Multi-class hierar- chical question classification for multiple choice sci- ence exams. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 5370- 5382, Marseille, France. European Language Re- sources Association.
- Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, and Wai Lam. 2021a. Exploiting reasoning chains for multi-hop science question answering. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1143-1156, Punta Cana, Do- minican Republic. Association for Computational Linguistics. · DOI
- Shunyu Yao, Karthik Narasimhan, and Matthew Hausknecht. 2021. Reading and acting while blind- folded: The need for semantics in text game agents. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, pages 3097-3102.
- Xusen Yin and Jonathan May. 2019. Learn how to cook a new recipe in a new house: Using map familiar- ization, curriculum learning, and bandit feedback to learn families of text-based adventure games. arXiv preprint arXiv:1908.04777. · arXiv
- Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yan- ping Huang, Jeff Dean, Noam Shazeer, and William Fedus. 2022. Designing effective sparse expert mod- els. arXiv preprint arXiv:2202.08906. · arXiv
Cited by
Sorted by citations
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970 · see citing works
A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024) · Vicinagearth · doi:10.1007/s44336-024-00009-2 · Cited by 404 · see citing works
Benchmarks for Automated Commonsense Reasoning: A Survey
Davis, E. (2023) · ACM Computing Surveys · doi:10.1145/3615355 · Cited by 84 · see citing works
From System 1 to System 2: A Survey of Reasoning Large Language Models
Zhang, D., Li, Z., Zhang, M.-L., Zhang, J., Liu, Z., Yao, Y., Xu, H., Zheng, J., Chen, X., Zhang, Y., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3637037 · Cited by 172 · see citing works
AgentBoard: An analytical evaluation board of multi-turn LLM agents
Ma, C., Zhang, J., Zhu, Z., Yang, C., Yang, Y., Jin, Y., Lan, Z., Kong, L., & He, J. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-2365 · Cited by 26 · see citing works
On Grounded Planning for Embodied Tasks with Language Models
Lin, B. Y., Huang, C., Liu, Q., Gu, W., Sommerer, S., & Ren, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26549 · Cited by 23 · see citing works
A Survey on the Optimization of Large Language Model-based Agents
Du, S., Zhao, J., Shi, J., Xie, Z., Jiang, X., Bai, Y., & He, L. (2026) · ACM Computing Surveys · doi:10.1145/3789261 · Cited by 38 · see citing works
A Survey on the Optimization of Large Language Model-based Agents
Du, S., Zhao, J., Shi, J., Xie, Z., Jiang, X., Bai, Y., & He, L. (2025) · arXiv · doi:10.48550/arxiv.2503.12434 · Cited by 22
Large Language Models Are Neurosymbolic Reasoners
Fang, M., Deng, S., Zhang, Y., Shi, Z., Chen, L., Pechenizkiy, M., & Wang, Y.-X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29754 · Cited by 28 · see citing works
A Survey of Reasoning with Foundation ModelsPreprint
Sun, J., Zheng, C., Xie, E., Liu, Z., Chu, R., Liu, J., Xu, J., Ding, M., Li, H., Geng, M., et al. (2023) · doi:10.31219/osf.io/ac4sp · Cited by 51 · see citing works
Fusing Pre-Trained Language Models with Multimodal Prompts through Reinforcement Learning
Yu, Y., Chung, J., Yun, H., Hessel, J., Park, J. S., Lu, X., Zellers, R., Ammanabrolu, P., Bras, R. J. L., Kim, G., et al. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01044 · Cited by 16 · see citing works
Self-citationCan Language Models Be Used in Multistep Commonsense Planning Domains?
Tang, Z., & Kejriwal, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-33469-6_28 · Cited by 13 · see citing works
Open-Ethical AI: Advancements in Open-Source Human-Centric Neural Language Models
Sicari, S., Moreno, J. F. C., Rizzardi, A., & Coen‐Porisini, A. (2024) · ACM Computing Surveys · doi:10.1145/3703454 · Cited by 10 · see citing works
Enhancing LLM Reasoning Capabilities Through Brokered Multi-Expert Reflection
Sheokand, T., Jain, G., Bahga, A., & Madisetti, V. K. (2025) · IEEE Access · doi:10.1109/access.2025.3561693 · Cited by 7 · see citing works
Liu, J., Hao, W., Cheng, K., & Jin, D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110319 · Cited by 5 · see citing works
AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
Anokhin, P., Semenov, N., Sorokin, A., Evseev, D., Kravchenko, A., Burtsev, M., & Burnaev, E. (2024) · arXiv · doi:10.48550/arxiv.2407.04363 · Cited by 8 · see citing works
Wang, Z., Teo, S. X., Chew, J. J., & Shi, W. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730009 · Cited by 4 · see citing works
TextWorldExpress: Simulating Text Games at One Million Steps Per Second
Jansen, P., & Côté, M.-A. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-demo.20 · Cited by 5 · see citing works
Self-citationBehavior Cloned Transformers are Neurosymbolic Reasoners
Wang, R., Jansen, P., Côté, M.-A., & Ammanabrolu, P. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.204 · Cited by 4 · see citing works
Self-citationAgentSquare: Automatic LLM Agent Search in Modular Design Space
Shang, Y., Li, Y., Zhao, K., Ma, L., Liu, J., Xu, F., & Li, Y. (2024) · arXiv · doi:10.48550/arxiv.2410.06153 · Cited by 3 · see citing works
Integrated Systems for Computational Scientific Discovery
Pat Langley, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30269 · Cited by 3 · see citing works
Applying Cognitive Design Patterns to General LLM Agents
Wray, R. E., Kirk, J. R., & Laird, J. E. (2025) · Artificial General Intelligence · doi:10.1007/978-3-032-00800-8_28 · Cited by 6 · see citing works
Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding
Zhu, L., Zhao, R., Gui, L., & He, Y. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.677 · Cited by 5 · see citing works
WESE: weak exploration to strong exploitation for LLM agents
Huang, X., Liu, W., Chen, X., Wang, X., Lian, D., Wang, Y., Tang, R., & Chen, E. (2026) · Science China Information Sciences · doi:10.1007/s11432-024-4554-x · Cited by 5 · see citing works
Knowledge-enhanced Agents for Interactive Text Games
Chhikara, P., Zhang, J., Ilievski, F., Francis, J., & Ma, K. (2023) · Proceedings of the 12th Knowledge Capture Conference 2023 · doi:10.1145/3587259.3627561 · Cited by 2 · see citing works
Warnakulasuriya, K., Dissanayake, P., Silva, N. D., Cranefield, S., Savarimuthu, B. T. R., Ranathunga, S., & de Silva, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-17542-7_7 · Cited by 2 · see citing works
Story Shaping: Teaching Agents Human-Like Behavior with Stories
Peng, X., Cui, C., Zhou, W. G., Jia, R., & Riedl, M. O. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27528 · Cited by 2 · see citing works
Continually Learning Planning Agent for Large Environments guided by LLMs
Paul, S. K. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00076 · Cited by 2 · see citing works
RRdE: A Decision Making Framework for Language Agents in Interactive Environments
Zhou, X., Li, L., & Zeng, D. D. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650094 · Cited by 3 · see citing works
Transferring Procedural Knowledge Across Commonsense Tasks
Jiang, Y., Ilievski, F., & Ma, K. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230391 · Cited by 2 · see citing works
Yu, Y., Yao, L., Xie, Y., Tan, Q., Feng, J., Li, Y., & Wu, L. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.981 · Cited by 4 · see citing works
Jordan, J., Hakimov, S., & Schlangen, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02551-7_6 · Cited by 1 · see citing works
Zhang, Z., Cheng, B., & He, B. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3637862 · Cited by 2 · see citing works
Science-Gym: a simple testbed for AI-driven scientific discovery
Cerrato, M., Baur, L., Brugger, J., Shumaly, S., Schmitt, N., Finkelstein, E., Jukic, S., Münzel, L., Paul, F. P., Pfannes, P., et al. (2026) · Machine Learning · doi:10.1007/s10994-025-06914-x · Cited by 2 · see citing works
Agentic AI Safety: A Structured Review of Open Problems and Their Regulatory Anchoring
Valenta, T., Rozinek, O., & Horálek, J. (2026) · Applied Informatics · doi:10.3390/ai7080298 · Cited by 1 · see citing works
Wang, R., Todd, G., Yuan, X., Xiao, Z., Côté, M.-A., & Jansen, P. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.830 · Cited by 2 · see citing works
Self-citationPeng, S., Hu, X., Yi, Q., Zhang, R., Guo, J., Huang, D., Tian, Z., Chen, R., Du, Z., Guo, Q., et al. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i13.29376 · Cited by 5 · see citing works
Teodorescu, L. (2023) · theses.fr (ABES) · doi:10.70675/08e0bf33z987fz4ff6zbdd7zbf6cf87e81f0 · Cited by 1 · see citing works
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution
Shang, Z., Huo, Y., Gong, M., Yan, A., Qu, Z., Dong, J., Low, B. K. H., Wu, C., & Dai, Z. (2026) · arXiv · doi:10.48550/arxiv.2610.05300
ADIAS: Automated Design of Interactive Agentic Systems
Jiang, L., Tang, B., Goetz, S., & Guo, Y. (2026) · arXiv · doi:10.48550/arxiv.2608.06410
Yu, Y., Yao, L., Xie, Y., Tan, Q., Feng, J., Li, Y., & Wu, L. (2026) · arXiv · doi:10.48550/arxiv.2601.01885
Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents
Teodorescu, L., Yuan, X., Côté, M.-A., & Oudeyer, P. (2022) · doi:10.18653/v1/2022.wordplay-1.5
Self-citationDiffG-RL: Leveraging Difference between Environment State and Common Sense
Tanaka, T., Kimura, D., & Tatsubori, M. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.110
Self-Supervised Behavior Cloned Transformers are Path Crawlers for Text Games
Wang, R., & Jansen, P. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.369
Self-citationAdvancing Large Language Model Agent via Iterative Contrastive Trajectory Optimization
Jing, C., Jing, X., & Li, K. (2024) · International Journal of Advanced Network Monitoring and Controls · doi:10.2478/ijanmc-2024-0033
A Novel Visual-Enhanced Dual Stream Long-Term Decision Framework for Large Language Model Agents
Wang, X., Zhao, J., Shi, J., Li, L., & Zeng, D. D. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-6599-0_23
AoPSFT: Subplan-Aware Fine-Tuning for Interpretable Multi-turn Reasoning Agents
Zhou, X., Geng, J., Cai, C., Li, L., & Zeng, D. D. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4088-4_12
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
Min, T. D., Roy, S., Lathuilière, S., Ricci, E., & Mancini, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37235-2_30
LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents
Lorenzoni, G., Alencar, P., & Cowan, D. D. (2026) · International Workshop on Agentic Engineering · doi:10.1145/3786167.3788429
LLM-FDC: LLM-Driven Fuzzy Rule Generation and Confidence-Based Decision-Making
Han, S., Hu, T., & Ma, H. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-1635-2_24
AdaInertia: Dynamic Tool Usage Inertia Control via Deep Q-Learning for Efficient LLM Agent Reasoning
Hu, Y., Zhao, Y., Huang, Y., Dong, G., Zhang, B., Di, M., & Wang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3381-6_37
MemHRL: Aligning Hierarchical Memory and Policy Learning for Long-Horizon LLM AgentsPreprint
Yin, X., Huang, C., Liu, R., & Ning, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-11435233/v1
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
Yuan, S., Song, K., Chen, J., Tan, X., Li, D., & Yang, D. (2024) · arXiv · doi:10.48550/arxiv.2406.14228
DORA Explorer: Improving the Exploration Ability of LLMs Without Training
Gurjar, P., Ishmam, M. F., & Marino, K. (2026) · arXiv · doi:10.48550/arxiv.2604.17244
- Authors
- Wang, R., Jansen, P., Côté, M.-A., & Ammanabrolu, P.
- Affiliations
- University of Arizona (US)
- Microsoft Research Montréal (Canada) (CA)
- Allen Institute for Artificial Intelligence (US)
- Venue
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Published
- 2022
- Pages
- 11279-11298
- OpenAlex
- W4221161476
- Cited by
- 45
- References
- 0
- Citations by year
- 2026: 10 · 2025: 10 · 2024: 8 · 2023: 14 · 2022: 3
- FWCI
- 3.17
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1815948)
- Allen Institute for Artificial Intelligence
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Social Sciences › Education › Science Education and Pedagogy
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Keywords
- scientific reasoning, elementary school science curriculum, interactive learning, large language models, scientific question answering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
