Elamur Research⌕
☰
home / papers / 2025 / HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model

Paper · 2025 · Mengkang Hu, Tianxing Chen, Qiguang Chen et al.

Summary

LLM-based agents often keep every past action-observation pair in their prompt. On long-horizon tasks this context grows large and repetitive, which makes it harder for the model to keep a consistent plan. Prior work has mostly optimized memory carried across attempts (cross-trial). This paper instead focuses on memory within a single attempt (working memory). The authors draw on the cognitive-science idea of chunking and propose HiAgent. In HiAgent, the LLM first sets a subgoal and then acts toward it. Once the subgoal is reached, its detailed steps are condensed into a short summary that also records whether the subgoal succeeded. Full detail is kept only for the subgoal currently in progress. A trajectory retrieval module can restore the detailed history of an earlier subgoal when needed, for example to diagnose a failure. The method was tested on five long-horizon tasks from AgentBoard. Compared with the STANDARD full-history approach, HiAgent roughly doubles the success rate while using fewer steps, shorter context and less runtime. This suggests that managing working memory, and not only planning, is an important factor in agent performance.

Key points

  • Overall results on five AgentBoard tasks:
    • Average success rate rose from 21 to 42 compared with STANDARD.
    • Progress rate improved by 23.94%.
    • Average number of steps fell by 3.8.
  • Efficiency: context length dropped by 35.02% and runtime by 19.42% relative to STANDARD.
  • Ablation on tyreworld: the comparison was against a task-decomposition variant ("w. TD") that creates subgoals but keeps all detailed history.
    • Success rate: STANDARD 10, w. TD 40, HiAgent 60.
    • Steps: 28.4, 22.8 and 19.0 respectively.
    • Context: w. TD grew to 112.8% of the baseline, while HiAgent shrank to 73.6%.
  • Robustness over long runs: HiAgent's progress-rate advantage holds across step counts. Its actions are also more likely to be executable as the number of steps increases.
  • Compatibility: the authors present the framework as applicable on top of other agent designs, such as ReAct thought-action-observation traces, and possibly multi-agent systems. Code is available at github.com/HiAgent2024/HiAgent.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Harbin Institute of TechnologyHarbin · China158 works · 28,841 citations🎓University of Hong KongPok Fu Lam · China89 works · 11,774 citations🔬Shanghai Artificial Intelligence LaboratoryShanghai · China117 works · 11,281 citations

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 works

Cite

Cite as Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao and Ping Luo. 2025. HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.1575

@inproceedings{hu2025hiagent,
  title = {{HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model}},
  author = {Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao and Ping Luo},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.1575},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1575}
}

References

83 references, 33 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mohamed Aghzal, Erion Plaku, and Ziyu Yao. 2023. Can large language models be good path planners? a benchmark and investigation on spatial-temporal reasoning. arXiv preprint arXiv:2310.03249.
  2. Nick Alonso, Tomás Figliolia, Anthony Ndirango, and Beren Millidge. 2024. Toward conversational agents with context and time sensitive long-term memory. arXiv preprint arXiv:2406.00057. — [arXiv:2406.00057](https://arxiv.org/abs/2406.00057) find
  3. Chenxin An, Shansan Gong, Ming Zhong, Mukai Li, Jun Zhang, Lingpeng Kong, and Xipeng Qiu. 2023. L-eval: Instituting standardized evaluation for long context language models. arXiv preprint arXiv:2307.11088.
  4. John R Anderson. 2013. The architecture of cognition. Psychology Press. find
  5. Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade, Arun Iyer, Suresh Parthasarathy, Sriram Rajamani, B Ashok, and Shashank Shet. 2024. Codeplan: Repository-level coding using llms and planning. Proceedings of the ACM on Software Engineering, 1(FSE):675–698. find
  6. Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.
  7. Amanda Bertsch, Uri Alon, Graham Neubig, and Matthew Gormley. 2024. Unlimiformer: Long-range transformers with unlimited length input. Advances in Neural Information Processing Systems, 36. find
  8. Nuo Chen, Hongguang Li, Juhua Huang, Baoyuan Wang, and Jia Li. 2024a. Compress to impress: Unleashing the potential of compressive memory in real-world long-term conversations. arXiv preprint arXiv:2402.11975. find
  9. Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025. Towards reasoning era: A survey of long chain-of-thought for reasoning large language models. arXiv preprint arXiv:2503.09567.
  10. Qiguang Chen, Libo Qin, Jiaqi Wang, Jingxuan Zhou, and Wanxiang Che. 2024b. Unlocking the capabilities of thought: A reasoning boundary framework to quantify and optimize chain-of-thought. Advances in Neural Information Processing Systems, 37:54872– 54904. find
  11. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chen Qian, Chi-Min Chan, Yujia Qin, Yaxi Lu, Ruobing Xie, et al. 2023. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848.
  12. Alexis Chevalier, Alexander Wettig, Anirudh Ajith, and Danqi Chen. 2023. Adapting language models to compress contexts. arXiv preprint arXiv:2305.14788.
  13. Jing Guo, Nan Li, Jianchuan Qi, Hang Yang, Ruiqiao Li, Yuzhen Feng, Si Zhang, and Ming Xu. 2023. Empowering working memory for large language model agents. arXiv preprint arXiv:2312.17259. — [arXiv:2312.17259](https://arxiv.org/abs/2312.17259) find
  14. Shibo Hao, Tianyang Liu, Zhen Wang, and Zhiting Hu. 2024. Toolkengpt: Augmenting frozen language models with massive tools via tool embeddings. Advances in neural information processing systems, 36.
  15. 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. find
  16. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, et al. 2023. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352.
  17. Chenxu Hu, Jie Fu, Chenzhuang Du, Simian Luo, Junbo Zhao, and Hang Zhao. 2023a. Chatdb: Augmenting llms with databases as their symbolic memory. arXiv preprint arXiv:2306.03901. — [arXiv:2306.03901](https://arxiv.org/abs/2306.03901) find
  18. Mengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu, Wenqi Shao, Qiguang Chen, Bin Wang, Yu Qiao, and Ping Luo. 2023b. Tree-planner: Efficient close-loop task planning with large language models. arXiv preprint arXiv:2310.08582. — [arXiv:2310.08582](https://arxiv.org/abs/2310.08582) find
  19. Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jian-guang Lou, Qingwei Lin, Ping Luo, Saravan Rajmohan, and Dongmei Zhang. 2024. Agentgen: Enhancing planning abilities for large language model based agent via environment and task generation. arXiv preprint arXiv:2408.00764. — [arXiv:2408.00764](https://arxiv.org/abs/2408.00764) find
  20. Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022a. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning, pages 9118–9147. PMLR.
  21. Wenlong Huang, Fei Xia, Dhruv Shah, Danny Driess, Andy Zeng, Yao Lu, Pete Florence, Igor Mordatch, Sergey Levine, Karol Hausman, and Brian Ichter. 2023. Grounded decoding: Guiding text generation with grounded models for robot control. Preprint, arXiv:2303.00855. — [arXiv:2303.00855](https://arxiv.org/abs/2303.00855) find
  22. Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, Pierre Sermanet, Noah Brown, Tomas Jackson, Linda Luu, Sergey Levine, Karol Hausman, and Brian Ichter. 2022b. Inner monologue: Embodied reasoning through planning w… find
  23. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. find
  24. Tomoyuki Kagaya, Thong Jing Yuan, Yuxuan Lou, Jayashree Karlekar, Sugiri Pranata, Akira Kinose, Koki Oguri, Felix Wick, and Yang You. 2024. Rap: Retrieval-augmented planning with contextual memory for multimodal llm agents. arXiv preprint arXiv:2402.03610. — [arXiv:2402.03610](https://arxiv.org/abs/2402.03610) find
  25. Hao Kang and Chenyan Xiong. 2024. Researcharena: Benchmarking llms’ ability to collect and organize information as research agents. arXiv preprint arXiv:2406.10291. — [arXiv:2406.10291](https://arxiv.org/abs/2406.10291) find
  26. Eric Li and Jim Waldo. 2024. Websuite: Systematically evaluating why web agents fail. arXiv preprint arXiv:2406.01623. — [arXiv:2406.01623](https://arxiv.org/abs/2406.01623) find
  27. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023a. Camel: Communicative agents for" mind" exploration of large language model society. Advances in Neural Information Processing Systems, 36:51991–52008.
  28. Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, and Yongbin Li. 2023b. Api-bank: A comprehensive benchmark for tool-augmented llms. arXiv preprint arXiv:2304.08244.
  29. Xinnian Liang, Bing Wang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, and Zhoujun Li. 2023. Unleashing infinite-length input capacity for large-scale language models with self-controlled memory system. arXiv e-prints, pages arXiv–2304. find
  30. Xi Victoria Lin, Chenglong Wang, Luke Zettlemoyer, and Michael D Ernst. 2018. Nl2bash: A corpus and semantic parser for natural language interface to the linux operating system. arXiv preprint arXiv:1802.08979. find
  31. Bo Liu, Yuqian Jiang, Xiaohan Zhang, Qiang Liu, Shiqi Zhang, Joydeep Biswas, and Peter Stone. 2023a. Llm+ p: Empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477.
  32. Lei Liu, Xiaoyan Yang, Yue Shen, Binbin Hu, Zhiqiang Zhang, Jinjie Gu, and Guannan Zhang. 2023b. Think-in-memory: Recalling and post-thinking enable llms with long-term memory. arXiv preprint arXiv:2311.08719. — [arXiv:2311.08719](https://arxiv.org/abs/2311.08719) find
  33. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12:157–173.
  34. Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2023c. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688.
  35. Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, and Junxian He. 2024. Agentboard: An analytical evaluation board of multi-turn llm agents. arXiv preprint arXiv:2401.13178. find
  36. Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of llm agents. arXiv preprint arXiv:2402.17753. find
  37. Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Peter Jansen, Oyvind Tafjord, Niket Tandon, Li Zhang, Chris Callison-Burch, and Peter Clark. 2023. Clin: A continually learning language agent for rapid task adaptation and generalization. arXiv preprint arXiv:2310.10134.
  38. Meta AI. 2024. Introducing meta Llama 3: The most capable openly available LLM to date. Accessed: 2024-04-18. find
  39. George A Miller. 1956. The magical number seven, plus or minus two: Some limits on our capacity for processing information. Psychological review, 63(2):81. find
  40. Yao Mu, Junting Chen, Qinglong Zhang, Shoufa Chen, Qiaojun Yu, Chongjian Ge, Runjian Chen, Zhixuan Liang, Mengkang Hu, Chaofan Tao, et al. 2024a. Robocodex: Multimodal code generation for robotic behavior synthesis. arXiv preprint arXiv:2402.16117. — [arXiv:2402.16117](https://arxiv.org/abs/2402.16117) find
  41. Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, and Ping Luo. 2024b. Embodiedgpt: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems, 36. find
  42. Allen Newell, Herbert Alexander Simon, et al. 1972. Human problem solving, volume 104. Prentice-hall Englewood Cliffs, NJ. find
  43. OpenAI. 2022. Openai: Introducing chatgpt. find
  44. OpenAI. 2023. Gpt-4 technical report. arXiv:2303.08774.
  45. Preprint, Yichen Pan, Dehan Kong, Sida Zhou, Cheng Cui, Yifei Leng, Bing Jiang, Hangyu Liu, Yanyi Shang, Shuyan Zhou, Tongshuang Wu, et al. 2024. Webcanvas: Benchmarking web agents in online environments. arXiv preprint arXiv:2406.12373. — [arXiv:2406.12373](https://arxiv.org/abs/2406.12373) find
  46. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. find
  47. Xavier Puig, Kevin Ra, Marko Boben, Jiaman Li, Tingwu Wang, Sanja Fidler, and Antonio Torralba. 2018. Virtualhome: Simulating household activities via programs. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8494–8502. find
  48. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789.
  49. Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Xingyu Zeng, and Rui Zhao. 2023. Tptu: Task planning and tool usage of large language model-based ai agents. arXiv preprint arXiv:2308.03427. language model based autonomous agents. Frontiers of Compu… — [arXiv:2308.03427](https://arxiv.org/abs/2308.03427) find
  50. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. 2023a. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091. find
  51. Xingyao Wang, Zihan Wang, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, and Heng Ji. 2023b. Mint: Evaluating llms in multi-turn interaction with tools and language feedback. arXiv preprint arXiv:2309.10691.
  52. Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, and Joel Veness. 2023. Randomized positional encodings boost length generalization of transformers. arXiv preprint arXiv:2305.16843. find
  53. Zihao Wang, Shaofei Cai, Anji Liu, Yonggang Jin, Jinbing Hou, Bowei Zhang, Haowei Lin, Zhaofeng He, Zilong Zheng, Yaodong Yang, et al. 2023c. Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language models. arXiv preprint arXiv:2311.05997. find
  54. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2024. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36.
  55. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.
  56. Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2020. Alfworld: Aligning text and embodied environments for interactive learning. arXiv preprint arXiv:2010.03768.
  57. Robert F Woolson. 2005. Wilcoxon signed-rank test. Encyclopedia of Biostatistics, 8. find
  58. Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, and Animesh Garg. 2023. Progprompt: Generating situated robot task plans using large language models. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 1…
  59. Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M. Sadler, Wei-Lun Chao, and Yu Su. 2023. Llm-planner: Few-shot grounded planning for embodied agents with large language models. Preprint, arXiv:2212.04088.
  60. XAgent Team. 2023. Xagent: An autonomous agent for complex task solving. find
  61. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  62. Mengsong Wu, Tong Zhu, Han Han, Chuanyuan Tan, Xiang Zhang, and Wenliang Chen. 2024. Seal-tools: Self-instruct tool learning dataset for agent tuning and detailed benchmark. arXiv preprint arXiv:2405.08355. — [arXiv:2405.08355](https://arxiv.org/abs/2405.08355) find
  63. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155.
  64. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  65. Chaojun Xiao, Pengle Zhang, Xu Han, Guangxuan Xiao, Yankai Lin, Zhengyan Zhang, Zhiyuan Liu, Song Han, and Maosong Sun. 2024. Infllm: Unveiling the intrinsic capacity of llms for understanding extremely long sequences with training-free memory. arXiv preprint arXiv:2402.04617.
  66. Shangqing Tu, Chunyang Li, Jifan Yu, Xiaozhi Wang, Lei Hou, and Juanzi Li. 2023. Chatlog: Recording and analyzing chatgpt across time. arXiv preprint arXiv:2304.14106. — [arXiv:2304.14106](https://arxiv.org/abs/2304.14106) find
  67. Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, and Yu Su. 2024. Travelplanner: A benchmark for real-world planning with language agents. arXiv preprint arXiv:2402.01622. find
  68. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. 2024. A survey on large Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, et al. 2023. Openagents: An ope…
  69. Siwei Yang, Bingchen Zhao, and Cihang Xie. 2024. Aqa-bench: An interactive benchmark for evaluating llms’ sequential reasoning ability. arXiv preprint arXiv:2402.09404. — [arXiv:2402.09404](https://arxiv.org/abs/2402.09404) find
  70. Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. 2022a. Webshop: Towards scalable real-world web interaction with grounded language agents. Advances in Neural Information Processing Systems, 35:20744–20757.
  71. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36. find
  72. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022b. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
  73. Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memorybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19724–19731. find
  74. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, et al. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625.
  75. Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Yonatan Bisk, Daniel Fried, Uri Alon, et al. 2023a. Webarena: A realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854.
  76. Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell, and Mrinmaya Sachan. 2023b. Recurrentgpt: Interactive generation of (arbitrarily) long text. arXiv preprint arXiv:2305.13304.
  77. Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh Murthy, Zeyuan Chen, Jianguo Zhang, Devansh Arpit, et al. 2023. Retroformer: Retrospective large language agents with policy gradient optimization. arXiv preprint arXiv:2308.02151. — [arXiv:2308.02151](https://arxiv.org/abs/2308.02151) find
  78. Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, and Bill Yuchen Lin. 2023. Lumos: Learning agents with unified data, modular design, and open-source llms. arXiv preprint arXiv:2311.05657. find
  79. Ruifeng Yuan, Shichao Sun, Zili Wang, Ziqiang Cao, and Wenjie Li. 2023. Evolving large language model assistant with long-term conditional memory. arXiv preprint arXiv:2312.17257. — [arXiv:2312.17257](https://arxiv.org/abs/2312.17257) find
  80. Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B Tenenbaum, Tianmin Shu, and Chuang Gan. 2023a. Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485. find
  81. Jiajie Zhang, Shulin Cao, Tingjia Zhang, Xin Lv, Jiaxin Shi, Qi Tian, Juanzi Li, and Lei Hou. 2023b. Reasoning over hierarchical question decomposition tree for explainable question answering. arXiv preprint arXiv:2305.15056. find
  82. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2024. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501. find
  83. Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. 2024. Expel: Llm agents are experiential learners. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19632–19642. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hu-2025-hiagent-hierarchical-working-memory-management/