{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:51:35Z","timestamp":1773211895224,"version":"3.50.1"},"reference-count":49,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Large language models (LLMs) have shown remarkable capabilities in solving complex tasks. Recent work has explored decomposing such tasks into subtasks with independent contexts. However, some contextually related subtasks may encounter information loss during execution, leading to redundant operations or execution failures. To address this issue, we propose a training-free framework with an interaction mechanism, which enables a subtask to query specific information or trigger certain actions in completed subtasks by sending requests. To implement interaction, we introduce a subtask trajectory memory to enable the resumption of completed subtasks upon receiving interaction requests. Additionally, we propose a new action during execution, which generates a concise and precise description of the execution process and outcomes of a subtask, to assist subsequent subtasks in determining interaction targets and requests. Our framework achieves 46.0% and 52.6% success rates on WebShop and HotpotQA, outperforming the strong baselines by 1.0 and 2.6 absolute percentage points, respectively.<\/jats:p>","DOI":"10.3390\/info17030274","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T08:43:31Z","timestamp":1773132211000},"page":"274","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Training-Free LLM Framework with Interaction Between Contextually Related Subtasks in Solving Complex Tasks"],"prefix":"10.3390","volume":"17","author":[{"given":"Hongjia","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"ref_1","unstructured":"Zhou, S., Xu, F.F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y., and Fried, D. (2024, January 7\u201311). WebArena: A Realistic Web Environment for Building Autonomous Agents. Proceedings of the The Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_2","unstructured":"Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., and Yang, K. (2024, January 7\u201311). AgentBench: Evaluating LLMs as Agents. Proceedings of the The Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_3","unstructured":"Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., and Anandkumar, A. (2023). Voyager: An Open-Ended Embodied Agent with Large Language Models. arXiv."},{"key":"ref_4","unstructured":"Szot, A., Schwarzer, M., Agrawal, H., Mazoure, B., Metcalf, R., Talbott, W., Mackraz, N., Hjelm, R.D., and Toshev, A.T. (2024, January 7\u201311). Large Language Models as Generalizable Policies for Embodied Tasks. Proceedings of the The Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_5","unstructured":"Sun, Q., Liu, Z., Ma, C., Ding, Z., Xu, F., Yin, Z., Zhao, H., Wu, Z., Cheng, K., and Liu, Z. (2025). ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows. arXiv."},{"key":"ref_6","unstructured":"Lu, C., Lu, C., Lange, R.T., Foerster, J., Clune, J., and Ha, D. (2024). The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery. arXiv."},{"key":"ref_7","unstructured":"Xie, T., Zhang, D., Chen, J., Li, X., Zhao, S., Cao, R., Hua, T.J., Cheng, Z., Shin, D., and Lei, F. (2024, January 9\u201315). OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. Proceedings of the The Thirty-Eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, Vancouver, BC, Canada."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, X., Xiong, T., Yi, B., Wei, Z., Xiao, R., Chen, Y., Ye, J., Tao, M., Zhou, X., and Zhao, Z. (2025). OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use. arXiv.","DOI":"10.20944\/preprints202412.2294.v1"},{"key":"ref_9","unstructured":"Miserendino, S., Wang, M., Patwardhan, T., and Heidecke, J. (2025). SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bouzenia, I., and Pradel, M. (2025). Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories. arXiv.","DOI":"10.1109\/ASE63991.2025.00234"},{"key":"ref_11","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2022). React: Synergizing reasoning and acting in language models. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Yang, T., Xu, K., Feng, D., Yang, C., Ding, B., and Wang, H. (2025). Enhancing decision-making for LLM agents via step-level Q-value models. Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence, 25 February\u20134 March 2025, AAAI Press. AAAI\u201925\/IAAI\u201925\/EAAI\u201925.","DOI":"10.1609\/aaai.v39i25.34924"},{"key":"ref_13","unstructured":"Rozanov, N., and Rei, M. (2024). StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models. arXiv."},{"key":"ref_14","unstructured":"Dziri, N., Lu, X., Sclar, M., Li, X.L., Jiang, L., Lin, B.Y., West, P., Bhagavatula, C., Bras, R.L., and Hwang, J.D. (2023). Faith and Fate: Limits of Transformers on Compositionality. arXiv."},{"key":"ref_15","unstructured":"Shi, F., Chen, X., Misra, K., Scales, N., Dohan, D., Chi, E.H., Sch\u00e4rli, N., and Zhou, D. (2023, January 23\u201329). Large language models can be easily distracted by irrelevant context. Proceedings of the International Conference on Machine Learning, PMLR, Honolulu, HI, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, N.F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P. (2023). Lost in the Middle: How Language Models Use Long Contexts. arXiv.","DOI":"10.1162\/tacl_a_00638"},{"key":"ref_17","unstructured":"Khot, T., Trivedi, H., Finlayson, M., Fu, Y., Richardson, K., Clark, P., and Sabharwal, A. (2022). Decomposed Prompting: A Modular Approach for Solving Complex Tasks. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sun, S., Liu, Y., Wang, S., Zhu, C., and Iyyer, M. (2023). PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents. arXiv.","DOI":"10.18653\/v1\/2024.eacl-long.29"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Prasad, A., Koller, A., Hartmann, M., Clark, P., Sabharwal, A., Bansal, M., and Khot, T. (2024, January 16\u201321). ADaPT: As-Needed Decomposition and Planning with Language Models. Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico.","DOI":"10.18653\/v1\/2024.findings-naacl.264"},{"key":"ref_20","first-page":"58202","article-title":"Adaplanner: Adaptive planning from feedback with language models","volume":"36","author":"Sun","year":"2024","journal-title":"Thirty-Seventh Conference on Neural Information Processing Systems"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107200","DOI":"10.1016\/j.neunet.2025.107200","article-title":"TDAG: A multi-agent framework based on dynamic Task Decomposition and Agent Generation","volume":"185","author":"Wang","year":"2025","journal-title":"Neural Netw."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Schroeder, P., Morgan, N.W., Luo, H., and Glass, J.R. (May, January 29). THREAD: Thinking Deeper with Recursive Spawning. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, Albuquerque, NM, USA.","DOI":"10.18653\/v1\/2025.naacl-long.427"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., and Manning, C.D. (November, January 31). HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Qi, P., Lee, H., Sido, O., and Manning, C.D. (2020). Answering open-domain questions of varying reasoning steps from text. arXiv.","DOI":"10.18653\/v1\/2021.emnlp-main.292"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sun, C., Huang, S., and Pompili, D. (2024). Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs. arXiv.","DOI":"10.1109\/ICRA55743.2025.11128105"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yao, S., Chen, H., Yang, J., and Narasimhan, K. (2022). WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents. arXiv.","DOI":"10.52202\/068431-1508"},{"key":"ref_27","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Thirty-Seventh Conference on Neural Information Processing Systems"},{"key":"ref_28","first-page":"23813","article-title":"Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks","volume":"36","author":"Lin","year":"2024","journal-title":"Thirty-Seventh Conference on Neural Information Processing Systems"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R.K.W., and Lim, E.P. (2023). Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv.","DOI":"10.18653\/v1\/2023.acl-long.147"},{"key":"ref_30","unstructured":"Kim, S., Moon, S., Tabrizi, R., Lee, N., Mahoney, M.W., Keutzer, K., and Gholami, A. (2023). An LLM compiler for parallel function calling. arXiv."},{"key":"ref_31","unstructured":"Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S.K.S., and Lin, Z. (2024, January 7\u201311). MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. Proceedings of the The Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., and Cong, X. (2024, January 11\u201316). ChatDev: Communicative Agents for Software Development. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok, Thailand.","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"ref_33","unstructured":"Chen, W., Su, Y., Zuo, J., Yang, C., Yuan, C., Chan, C.M., Yu, H., Lu, Y., Hung, Y.H., and Qian, C. (2024, January 7\u201311). AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors. Proceedings of the The Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_34","unstructured":"Liu, Z., Zhang, Y., Li, P., Liu, Y., and Yang, D. (2024). Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization. arXiv."},{"key":"ref_35","unstructured":"Li, G., Hammoud, H.A.A.K., Itani, H., Khizbullin, D., and Ghanem, B. (2023, January 10\u201316). CAMEL: Communicative Agents for \u201dMind\u201d Exploration of Large Language Model Society. Proceedings of the Thirty-Seventh Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_36","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., and Hausman, K. (2022). Do as i can, not as i say: Grounding language in robotic affordances. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Hao, S., Gu, Y., Ma, H., Hong, J.J., Wang, Z., Wang, D.Z., and Hu, Z. (2023). Reasoning with language model is planning with world model. arXiv.","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref_38","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., and Yao, S. (2023, January 10\u201316). Reflexion: Language agents with verbal reinforcement learning. Proceedings of the 37th International Conference on Neural Information Processing Systems\u2014NIPS\u201923, New Orleans, LA, USA."},{"key":"ref_39","unstructured":"Ma, K., Zhang, H., Wang, H., Pan, X., Yu, W., and Yu, D. (2023). LASER: LLM Agent with State-Space Exploration for Web Navigation. arXiv."},{"key":"ref_40","unstructured":"Yang, Z., Li, P., Yan, M., Zhang, J., Huang, F., and Liu, Y. (2024). ReAct Meets ActRe: Autonomous Annotations of Agent Trajectories for Contrastive Self-Training. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kim, J., Rhee, S., Kim, M., Kim, D., Lee, S., Sung, Y., and Jung, K. (2025, January 4\u20139). ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China.","DOI":"10.18653\/v1\/2025.emnlp-main.1697"},{"key":"ref_42","unstructured":"Rawat, M., Gupta, A., Goomer, R., Bari, A.D., Gupta, N., and Pieraccini, R. (2025). Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents. arXiv."},{"key":"ref_43","unstructured":"Dongre, V., Yang, X., Acikgoz, E.C., Dey, S., Tur, G., and Hakkani-T\u00fcr, D. (2025). ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Chakraborty, T., Ghosh, U., Zhang, X., Niloy, F.F., Dong, Y., Li, J., Roy-Chowdhury, A., and Song, C. (2025, January 4\u20139). HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China.","DOI":"10.18653\/v1\/2025.findings-emnlp.1158"},{"key":"ref_45","unstructured":"Hadeliya, T., Jauhar, M.A., Sakpal, N., and Cruz, D. (2025). When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents. arXiv."},{"key":"ref_46","unstructured":"Zhou, A., Yan, K., Shlapentokh-Rothman, M., Wang, H., and Wang, Y.X. (2024, January 21\u201327). Language agent tree search unifies reasoning, acting, and planning in language models. Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_47","unstructured":"Zhang, T., Madaan, A., Gao, L., Zheng, S., Mishra, S., Yang, Y., Tandon, N., and Alon, U. (2024). In-context principle learning from mistakes. arXiv."},{"key":"ref_48","unstructured":"Yao, W., Heinecke, S., Niebles, J.C., Liu, Z., Feng, Y., Xue, L., Ramapura Narasimha Murthy, R., Chen, Z., Zhang, J., and Arpit, D. (2024, January 7\u201311). Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_49","unstructured":"Shridhar, M., Yuan, X., C\u00f4t\u00e9, M.A., Bisk, Y., Trischler, A., and Hausknecht, M. (2020). ALFWorld: Aligning Text and Embodied Environments for Interactive Learning. arXiv."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/3\/274\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T09:05:56Z","timestamp":1773133556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/3\/274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":49,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["info17030274"],"URL":"https:\/\/doi.org\/10.3390\/info17030274","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]}}}