Elamur Research⌕
☰
home / papers / 2026 / A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks

A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks

Paper · 2026 · Shuzheng Si, Haozhe Zhao, Kangyang Luo et al.

Summary

LLM-based agents on long, multi-step tasks often flail. Without an overall plan, they fall into aimless trial-and-error and produce hallucinated actions. Prior fixes either teach planning implicitly via SFT or RL on the executor, which needs lots of data or converges slowly, or supply explicit guidance that depends on manual data curation. The authors propose EAGLET, a plan-and-execute setup in which a separate, plug-and-play planner writes a global plan that the executor receives together with the task.

The planner is trained in two stages without human labeling. First, a strong reasoning LLM derives plans and reasoning traces from gold trajectories. Homologous consensus filtering keeps only plans that help executors sharing one base model but differing in skill, and the surviving plans feed a cold-start SFT. Second, rule-based RL with an executor capability gain reward (ECGR) favors plans that help both weak and strong executors succeed in fewer steps.

On ScienceWorld, ALFWorld and WebShop, executors using the planner set new state-of-the-art results, while training costs fall about eightfold versus RL baselines. This offers a cheap, transferable way to give agents foresight.

Key points

  • Plan synthesis uses advanced reasoning LLMs such as GPT-5 and DeepSeek-V3.1-Think. Each is prompted with the task, the gold trajectory and a one-shot example plan.
  • Homologous executors in the main experiments are novice-level Llama-3.1-8B-Instruct and expert-level GiGPO-Llama-3.1-8B. They share pre-training and architecture and differ only in post-training.
  • ECGR rewards a plan when it raises task completion and reduces the number of interactions across executors of different capability levels.
  • Training is about 8× cheaper than applying RL-based methods directly to executors, with no manual effort or extra training data.
  • Stated limitations: experiments are text-only, the method relies on access to diverse executor agents, and API-based executors (e.g., GPT-4.1) were not tested.

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

🎓Tsinghua UniversityBeijing · China333 works · 87,019 citations🎓University of Illinois Urbana-ChampaignUrbana · United States184 works · 69,372 citations🎓Peking UniversityBeijing · China244 works · 39,359 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Shuzheng Si, Haozhe Zhao, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang and Maosong Sun. 2026. A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks. Proceedings of the 64th 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/v1/2026.acl-long.597

@inproceedings{si2026goal,
  title = {{A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks}},
  author = {Shuzheng Si, Haozhe Zhao, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang and Maosong Sun},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.597},
  url = {https://doi.org/10.18653/v1/2026.acl-long.597}
}

References

49 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Anthropic. 2025. Claude 3.7 sonnet system card. find
  2. Hyungjoo Chae, Namyoung Kim, Kai Tzu iunn Ong, Minju Gwak, Gwanwoo Song, Jihoon Kim, Sunghwan Kim, Dongha Lee, and Jinyoung Yeo. 2025. Web agents with world models: Learning and leveraging environment dynamics in web navigation. In The Thirteenth International Conference on Learning Representations. find
  3. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, H… — [arXiv:2506.23127](https://arxiv.org/abs/2506.23127) find
  4. Lang Feng, Zhenghai Xue, Tingcong Liu, and Bo An. 2025. Group-in-group policy optimization for llm agent training. Preprint, arXiv:2505.10978. find
  5. Yao Fu, Dong-Ki Kim, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, and Honglak Lee. 2024. Autoguide: Automated generation and selection of context-aware guidelines for large language model agents. Preprint, arXiv:2403.08978. — [arXiv:2403.08978](https://arxiv.org/abs/2403.08978) find
  6. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao,… — The Llama 3 Herd of Models
  7. Jian Guan, Wei Wu, zujie wen, Peng Xu, Hongning Wang, and Minlie Huang. 2024. AMOR: A recipe for building adaptable modular knowledge agents through process feedback. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  8. Zican Hu, Wei Liu, Xiaoye Qu, Xiangyu Yue, Chunlin Chen, Zhi Wang, and Yu Cheng. 2025. Divide and conquer: Grounding LLMs as efficient decision-making agents via offline hierarchical reinforcement learning. In Forty-second International Conference on Machine Learning. find
  9. Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Hao Wang, Defu Lian, Yasheng Wang, Ruiming Tang, and Enhong Chen. 2024. Understanding the planning of llm agents: A survey. Preprint, arXiv:2402.02716. find
  10. Kimi-Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, Zhuofu Chen, Jialei Cui, Hao Ding, Mengnan Dong, Angang Du, Chenzhuang Du, Dikang Du, Yulun Du, Yu Fan, Yichen Feng, Kelin Fu, Bofei Gao, Hongcheng Gao, Peizhong Gao, Tong G… — Kimi K2: Open Agentic Intelligence
  11. Diederik P. Kingma and Jimmy Ba. 2017. Adam: A method for stochastic optimization. Preprint, arXiv:1412.6980.
  12. Jing Yu Koh, Stephen McAleer, Daniel Fried, and Ruslan Salakhutdinov. 2024. Tree search for language model agents. Preprint, arXiv:2407.01476. find
  13. Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding, Yiming Qiu, Zhenning Yang, Yibo Huang, Jayanth Srinivasa, Myungjin Lee, Mosharaf Chowdhury, and Ang Chen. 2025. Curie: Toward rigorous and automated scientific experimentation with ai agents. Preprint, arXiv:2502.16069. find
  14. Yu Lei, Shuzheng Si, Wei Wang, Yifei Wu, Gang Chen, Fanchao Qi, and Maosong Sun. 2025. Rhi-noinsight: Improving deep research through control mechanisms for model behavior and context. arXiv preprint arXiv:2511.18743. — [arXiv:2511.18743](https://arxiv.org/abs/2511.18743) find
  15. Zelong Li, Wenyue Hua, Hao Wang, He Zhu, and Yongfeng Zhang. 2024. Formal-llm: Integrating formal language and natural language for controllable llm-based agents. Preprint, arXiv:2402.00798. — [arXiv:2402.00798](https://arxiv.org/abs/2402.00798) find
  16. OpenAI. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  17. OpenAI. 2025. Gpt-5 technical report. find
  18. Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. ChatDev: Communicative agents for software development. In Proceedings of the 62nd Annual Meeting of the Association for Computat…
  19. Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2024. Agent planning with world knowledge model. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  20. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. Preprint, arXiv:1707.06347. find
  21. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. Preprint, arXiv:2402.03300.
  22. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik R Narasimhan, and Shunyu Yao. 2023. Reflexion: language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems.
  23. Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Cote, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2021. {ALFW}orld: Aligning text and embodied environments for interactive learning. In International Conference on Learning Representations. find
  24. Shuzheng Si, Wentao Ma, Haoyu Gao, Yuchuan Wu, Ting-En Lin, Yinpei Dai, Hangyu Li, Rui Yan, Fei Huang, and Yongbin Li. 2023. SpokenWOZ: A large-scale speech-text benchmark for spoken task-oriented dialogue agents. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Ben… find
  25. Shuzheng Si, Qingyi Wang, Haozhe Zhao, Yuzhuo Bai, Guanqiao Chen, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, et al. 2025a. Faithlens: Detecting and explaining faithfulness hallucination. arXiv preprint arXiv:2512.20182.
  26. Shuzheng Si, Haozhe Zhao, Gang Chen, Yunshui Li, Kangyang Luo, Chuancheng Lv, Kaikai An, Fanchao Qi, Baobao Chang, and Maosong Sun. 2025b. GATEAU: Selecting influential samples for long context alignment. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, page…
  27. Shuzheng Si, Haozhe Zhao, Cheng Gao, Yuzhuo Bai, Zhitong Wang, Bofei Gao, Kangyang Luo, Wenhao Li, Yufei Huang, Gang Chen, et al. 2025c. Teaching large language models to maintain contextual faithfulness via synthetic tasks and reinforcement learning. arXiv preprint arXiv:2505.16483. — [arXiv:2505.16483](https://arxiv.org/abs/2505.16483) find
  28. Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, and Sujian Li. 2024a. AgentBank: Towards generalized LLM agents via fine-tuning on 50000+ interaction trajectories. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2124–2141, Mi… find
  29. Yifan Song, Weimin Xiong, Dawei Zhu, Wenhao Wu, Han Qian, Mingbo Song, Hailiang Huang, Cheng Li, Ke Wang, Rong Yao, Ye Tian, and Sujian Li. 2023. Restgpt: Connecting large language models with real-world restful apis. Preprint, arXiv:2306.06624.
  30. Yifan Song, Da Yin, Xiang Yue, Jie Huang, Sujian Li, and Bill Yuchen Lin. 2024b. Trial and error: Exploration-based trajectory optimization of LLM agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7584–7600, Bangkok, Tha…
  31. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6).
  32. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. 2023. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Lon… find
  33. Ruoyao Wang, Peter Jansen, Marc-Alexandre Côté, and Prithviraj Ammanabrolu. 2022. ScienceWorld: Is your agent smarter than a 5th grader? In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11279–11298, Abu Dhabi, United Arab Emirates. Association for Comp… find
  34. Yutong Wang, Pengliang Ji, Kaixin Li, Baolong Bi, Tao Feng, and Guillaume Sartoretti. 2025. Beyond policy optimization: A data curation flywheel for sparse-reward long-horizon planning. Preprint, arXiv:2508.03018. — [arXiv:2508.03018](https://arxiv.org/abs/2508.03018) find
  35. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022a. Emergent abilities of large language models. Transactions on M…
  36. Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, and Yongbin Li. 2024. Language models are super mario: Absorbing abilities from homologous models as a free lunch. In Forty-first International Conference on Machine Learning.
  37. Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yuxiao Dong, and Jie Tang. 2024. AgentTuning: Enabling generalized agent abilities for LLMs. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3053–3077, Bangkok, Thailand. Association for Computational Linguistics.
  38. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 2022b. Chain of thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
  39. 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. Preprint, arXiv:2404.13501. find
  40. Weimin Xiong, Yifan Song, Qingxiu Dong, Bingchan Zhao, Feifan Song, Xun Wang, and Sujian Li. 2025. Mpo: Boosting llm agents with meta plan optimization. Preprint, arXiv:2503.02682. find
  41. 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 Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fo… find
  42. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei… find
  43. Shunyu Yao, Howard Chen, John Yang, and Karthik R Narasimhan. 2022. Webshop: Towards scalable real-world web interaction with grounded language agents. In Advances in Neural Information Processing Systems.
  44. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations.
  45. Yining Ye, Xin Cong, Shizuo Tian, Jiannan Cao, Hao Wang, Yujia Qin, Yaxi Lu, Heyang Yu, Huadong Wang, Yankai Lin, Zhiyuan Liu, and Maosong Sun. 2023. Proagent: From robotic process automation to agentic process automation. Preprint, arXiv:2311.10751. — [arXiv:2311.10751](https://arxiv.org/abs/2311.10751) find
  46. Haozhe Zhao, Shuzheng Si, Liang Chen, Yichi Zhang, Maosong Sun, Baobao Chang, and Minjia Zhang. 2025. Looking beyond text: Reducing language bias in large vision-language models via multimodal dual-attention and soft-image guidance. In Proceedings of the 2025 Conference on Empirical Methods in Natur… find
  47. Wangchunshu Zhou, Yuchen Eleanor Jiang, Long Li, Jialong Wu, Tiannan Wang, Shi Qiu, Jintian Zhang, Jing Chen, Ruipu Wu, Shuai Wang, Shiding Zhu, Jiyu Chen, Wentao Zhang, Xiangru Tang, Ningyu Zhang, Huajun Chen, Peng Cui, and Mrinmaya Sachan. 2023. Agents: An open-source framework for autonomous lang… find
  48. Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, and Ningyu Zhang. 2025. KnowAgent: Knowledge-augmented planning for LLM-based agents. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 3709– 3732, Albuquerque, New M… find
  49. Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, and Bill Yuchen Lin. 2024. Agent lumos: Unified and modular training for open-source language agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/si-2026-goal-without-plan-is-just/