---
title: "Collaborative Multi-Agent Scripts Generation for Enhancing"
description: "The paper addresses a known weakness of vision-language models: multi-hop reasoning in… 44 references, cited by 4 papers here."
authors: ["Keyang Zhong", "Junlin Xie", "Hefeng Wu", "Haofeng Li", "Guanbin Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.774/"
doi: "10.18653/v1/2026.findings-acl.774"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhong-2026-collaborative-multi-agent-scripts-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhong-2026-collaborative-multi-agent-scripts-generation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/) / Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games

# Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games

**Authors:** Keyang Zhong, Junlin Xie, [Hefeng Wu](https://md.research.elamur.ai/free/en/authors/hefeng-wu/), Haofeng Li and Guanbin Li · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.774/) · [PDF](https://aclanthology.org/2026.findings-acl.774.pdf) · [DOI 10.18653/v1/2026.findings-acl.774](https://doi.org/10.18653/v1/2026.findings-acl.774) · [OpenAlex](https://openalex.org/W7166807104)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [4](https://md.research.elamur.ai/free/en/papers/zhong-2026-collaborative-multi-agent-scripts-generation/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses a known weakness of vision-language models: multi-hop reasoning in multi-player settings where information is incomplete or deliberately misleading. The authors use Murder Mystery games as a testbed. Large human-written script collections are scarce, so they build a collaborative multi-agent pipeline driven by strong LLMs such as Gemini 2.5Pro. Generation agents (OutlineAgent, CharacterAgent, ClueAgent, RoleplayAgent, QaAgent) produce story outlines, role scripts, textual and visual clues, role-play dialogues and QA pairs. Evaluation agents check the output: CriticAgent rates logical coherence, and ScoreAgent rates role-consistent behaviour during training. The synthetic data is combined with curated human data to train Qwen2.5-VL models (3B and 7B) in two stages. The first stage is Chain-of-Thought SFT. The second is GRPO reinforcement learning with agent-monitored rewards, including an image-clue matching reward. The trained models improve on narrative reasoning, hidden-fact extraction and deception-robust understanding. According to the authors, they reach state-of-the-art results among open-source systems and are competitive with proprietary models. This provides a scalable way to train and evaluate VLMs under adversarial, imperfect-information conditions.

## Key points
- **Data ablation on Qwen2.5-VL-3B-Instruct, human-annotated test sets only:**
  - Human plus synthetic data performs best: MMR 55.01, CMD 34.25, LSU 87.40, MIU 61.09.
  - Human-only data gives MMR 51.03; synthetic-only data gives MMR 48.35.
- **Training-stage ablations:**
  - Dropping SFT lowers scores across the board.
  - Dropping RL mainly hurts multi-hop reasoning and CMD (case analysis).
  - Dropping the image-clue reward mainly hurts MIU and MMR.
- **LLM-as-Judge setup:** the subjective RP and CMD scores are assessed by three judges: DeepSeek-r1, GPT-4o and Gemini-2.5-Pro.
- **Agreement between judges:** pairwise Pearson r is 0.79–0.87 for CMD and 0.64–0.72 for RP. Cohen's κ is 0.58 for CMD and 0.47 for RP.
- **Agreement with humans and limitations:**
  - Averaged LLM scores correlate with human ratings at Spearman ρ 0.71 (CMD) and 0.62 (RP).
  - Image-clue alignment for WhodunitBench still needs partial human checking.

*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

- [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) — University, Guangzhou, China · 53 works · 9,185 citations
- [Chinese University of Hong Kong, Shenzhen](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong-shenzhen/) — University, Shenzhen, China · 47 works · 2,596 citations

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Keyang Zhong, Junlin Xie, Hefeng Wu, Haofeng Li and Guanbin Li. 2026. Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhong2026collaborative,
  title = {{Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games}},
  author = {Keyang Zhong, Junlin Xie, Hefeng Wu, Haofeng Li and Guanbin Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.774},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.774}
}
```

- [← previous Coding Agents with Multimodal Browsing are Generalist Problem Solvers](https://md.research.elamur.ai/free/en/papers/soni-2026-coding-agents-multimodal-browsing-are/)
- [next → Contrastive Learning with Narrative Twins for Modeling Story Salience](https://md.research.elamur.ai/free/en/papers/sterner-2026-contrastive-learning-narrative-twins-modeling/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/)

## References

44 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. [Qwen2.5-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). Preprint, arXiv:2502.13…
2. Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Xing Gao, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang, and Jingren Zhou. 2024a. Socialbench: Sociality evaluation of role-playing conversational agents. Preprint, arXiv:2403.13679. [find](https://scholar.google.com/scholar?q=Hongzhan+Chen%2C+Hehong+Chen%2C+Ming+Yan%2C+Wenshen+Xu%2C+Xing+Gao%2C+Weizhou+Shen%2C+Xiaojun+Quan%2C+Chenliang+Li%2C+Ji+Zhang%2C+Fei+Huang%2C+and+Jingren+Zhou%2E+2024a%2E+Socialbench%3A+Sociality+evaluation+of+role%2Dplaying+co)
3. Kang Chen, Zheng Lian, Haiyang Sun, Rui Liu, Jiangyan Yi, Bin Liu, and Jianhua Tao. 2024b. Can deception detection go deeper? dataset, evaluation, and benchmark for deception reasoning. Preprint, arXiv:2402.11432. — [arXiv:2402.11432](https://arxiv.org/abs/2402.11432) [find](https://scholar.google.com/scholar?q=Kang+Chen%2C+Zheng+Lian%2C+Haiyang+Sun%2C+Rui+Liu%2C+Jiangyan+Yi%2C+Bin+Liu%2C+and+Jianhua+Tao%2E+2024b%2E+Can+deception+detection+go+deeper%3F+dataset%2C+evaluation%2C+and+benchmark+for+deception+reasoning%2E+Preprint%2C+arXi)
4. Zhiwei Chen, Yupeng Hu, Zhiheng Fu, Zixu Li, Jiale Huang, Qinlei Huang, and Yinwei Wei. 2026. Intent: Invariance and discrimination-aware noise mitigation for robust composed image retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 20463–20471. [find](https://scholar.google.com/scholar?q=Zhiwei+Chen%2C+Yupeng+Hu%2C+Zhiheng+Fu%2C+Zixu+Li%2C+Jiale+Huang%2C+Qinlei+Huang%2C+and+Yinwei+Wei%2E+2026%2E+Intent%3A+Invariance+and+discrimination%2Daware+noise+mitigation+for+robust+composed+image+retrieval%2E+In+Proce)
5. Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Xuemeng Song, and Liqiang Nie. 2025. Offset: Segmentation-based focus shift revision for composed image retrieval. In Proceedings of the ACM International Conference on Multimedia, page 6113–6122. [find](https://scholar.google.com/scholar?q=Zhiwei+Chen%2C+Yupeng+Hu%2C+Zixu+Li%2C+Zhiheng+Fu%2C+Xuemeng+Song%2C+and+Liqiang+Nie%2E+2025%2E+Offset%3A+Segmentation%2Dbased+focus+shift+revision+for+composed+image+retrieval%2E+In+Proceedings+of+the+ACM+International+)
6. DeepSeek-AI. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). Preprint, arXiv:2501.12948.
7. Haonan Dong, Kehan Jiang, Haoran Ye, Wenhao Zhu, Zhaolu Kang, and Guojie Song. 2026. [Neureasoner: Towards explainable, controllable, and unified reasoning via mixture-of-neurons](https://md.research.elamur.ai/free/en/papers/dong-2026-neureasoner-explainable-controllable-unified-reasoning/). Preprint, arXiv:2604.02972.
8. Haonan Dong, Wenhao Zhu, Guojie Song, and Liang Wang. 2025. AuroRA: Breaking low-rank bottleneck of loRA with nonlinear mapping. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Haonan+Dong%2C+Wenhao+Zhu%2C+Guojie+Song%2C+and+Liang+Wang%2E+2025%2E+AuroRA%3A+Breaking+low%2Drank+bottleneck+of+loRA+with+nonlinear+mapping%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Information+Processing+)
9. Google Gemini Team. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). Technical report.
10. DeepMind Google. 2023. Introducing gemini: our largest and most capable ai model. [find](https://scholar.google.com/scholar?q=DeepMind+Google%2E+2023%2E+Introducing+gemini%3A+our+largest+and+most+capable+ai+model%2E)
11. Ruiyan Han, Zhen Fang, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, and 1 others. 2026. [Unicorn: Towards self-improving unified multimodal models through self-generated supervision](https://md.research.elamur.ai/free/en/papers/fang-2026-unicorn-self-improving-unified-multimodal/). arXiv preprint arXiv:2601.03193.
12. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). Preprint, arXiv:2106.09685.
13. Kehan Jiang, Haonan Dong, Zhaolu Kang, Zhengzhou Zhu, and Guojie Song. 2026. [Foe: Forest of errors makes the first solution the best in large reasoning models](https://md.research.elamur.ai/free/en/papers/jiang-2026-foe-forest-errors-makes-first/). Preprint, arXiv:2604.02967.
14. Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, and Huan Liu. 2025a. From generation to judgment: Opportunities and challenges of llm-as-a-judge. Preprint, arXiv:2411.16594. [find](https://scholar.google.com/scholar?q=Dawei+Li%2C+Bohan+Jiang%2C+Liangjie+Huang%2C+Alimohammad+Beigi%2C+Chengshuai+Zhao%2C+Zhen+Tan%2C+Amrita+Bhattacharjee%2C+Yuxuan+Jiang%2C+Canyu+Chen%2C+Tianhao+Wu%2C+Kai+Shu%2C+Lu+Cheng%2C+and+Huan+Liu%2E+2025a%2E+From+generation)
15. Zixu Li, Yupeng Hu, Zhiwei Chen, Shiqi Zhang, Qinlei Huang, Zhiheng Fu, and Yinwei Wei. 2026. Habit: Chrono-synergia robust progressive learning framework for composed image retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 6762–6770. [find](https://scholar.google.com/scholar?q=Zixu+Li%2C+Yupeng+Hu%2C+Zhiwei+Chen%2C+Shiqi+Zhang%2C+Qinlei+Huang%2C+Zhiheng+Fu%2C+and+Yinwei+Wei%2E+2026%2E+Habit%3A+Chrono%2Dsynergia+robust+progressive+learning+framework+for+composed+image+retrieval%2E+In+Proceedings+)
16. Zongxia Li, Xiyang Wu, Hongyang Du, Fuxiao Liu, Huy Nghiem, and Guangyao Shi. 2025b. A survey of state of the art large vision language models: Alignment, benchmark, evaluations and challenges. arXiv preprint arXiv:2501.02189. — [arXiv:2501.02189](https://arxiv.org/abs/2501.02189) [find](https://scholar.google.com/scholar?q=Zongxia+Li%2C+Xiyang+Wu%2C+Hongyang+Du%2C+Fuxiao+Liu%2C+Huy+Nghiem%2C+and+Guangyao+Shi%2E+2025b%2E+A+survey+of+state+of+the+art+large+vision+language+models%3A+Alignment%2C+benchmark%2C+evaluations+and+challenges%2E+arXiv+)
17. Zeyu Liu, Yuhang Liu, Guanghao Zhu, Congkai Xie, Zhen Li, Jianbo Yuan, Xinyao Wang, Qing Li, Shing-Chi Cheung, Shengyu Zhang, Fei Wu, and Hongxia Yang. 2025. Infi-mmr: Curriculum-based unlocking multimodal reasoning via phased reinforcement learning in multimodal small language models. Preprint, arX… [find](https://scholar.google.com/scholar?q=Zeyu+Liu%2C+Yuhang+Liu%2C+Guanghao+Zhu%2C+Congkai+Xie%2C+Zhen+Li%2C+Jianbo+Yuan%2C+Xinyao+Wang%2C+Qing+Li%2C+Shing%2DChi+Cheung%2C+Shengyu+Zhang%2C+Fei+Wu%2C+and+Hongxia+Yang%2E+2025%2E+Infi%2Dmmr%3A+Curriculum%2Dbased+unlocking+multi)
18. Shichao Ma, Yunhe Guo, Jiahao Su, Qihe Huang, Zhengyang Zhou, and Yang Wang. 2026. Talk2image: A multi-agent system for multi-turn image generation and editing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 32437–32445. [find](https://scholar.google.com/scholar?q=Shichao+Ma%2C+Yunhe+Guo%2C+Jiahao+Su%2C+Qihe+Huang%2C+Zhengyang+Zhou%2C+and+Yang+Wang%2E+2026%2E+Talk2image%3A+A+multi%2Dagent+system+for+multi%2Dturn+image+generation+and+editing%2E+In+Proceedings+of+the+AAAI+Conference+o)
19. Arindam Mitra, Luciano Del Corro, Guoqing Zheng, Shweti Mahajan, Dany Rouhana, Andres Codas, Yadong Lu, Wei ge Chen, Olga Vrousgos, Corby Rosset, Fillipe Silva, Hamed Khanpour, Yash Lara, and Ahmed Awadallah. 2024. Agentinstruct: Toward generative teaching with agentic flows. Preprint, arXiv:2407.03… [find](https://scholar.google.com/scholar?q=Arindam+Mitra%2C+Luciano+Del+Corro%2C+Guoqing+Zheng%2C+Shweti+Mahajan%2C+Dany+Rouhana%2C+Andres+Codas%2C+Yadong+Lu%2C+Wei+ge+Chen%2C+Olga+Vrousgos%2C+Corby+Rosset%2C+Fillipe+Silva%2C+Hamed+Khanpour%2C+Yash+Lara%2C+and+Ahmed+Aw)
20. OpenAI. 2023. Gpt-4v(ision) system card. System card, OpenAI. Published September 25, 2023. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2023%2E+Gpt%2D4v%28ision%29+system+card%2E+System+card%2C+OpenAI%2E+Published+September+25%2C+2023%2E)
21. Davide Paglieri, Bartłomiej Cupiał, Sam Coward, Ulyana Piterbarg, Maciej Wołczyk, Akbir Khan, Eduardo Pignatelli, Łukasz Kuciński, Lerrel Pinto, Rob Fergus, Jakob Nicolaus Foerster, Jack Parker-Holder, and Tim Rocktäschel. 2024. Benchmarking agentic llm and vlm reasoning on games. arXiv preprint ar… — [arXiv:2411.13543](https://arxiv.org/abs/2411.13543) [find](https://scholar.google.com/scholar?q=Davide+Paglieri%2C+Bart%C5%82omiej+Cupia%C5%82%2C+Sam+Coward%2C+Ulyana+Piterbarg%2C+Maciej+Wo%C5%82czyk%2C+Akbir+Khan%2C+Eduardo+Pignatelli%2C+%C5%81ukasz+Kucin%CC%81ski%2C+Lerrel+Pinto%2C+Rob+Fergus%2C+Jakob+Nicolaus+Foerster%2C+Jack+Parker%2DHolde)
22. Guozhi Qiu, Zhiwei Chen, Zixu Li, Qinlei Huang, Zhiheng Fu, Xuemeng Song, and Yupeng Hu. 2026. Melt: Improve composed image retrieval via the modification frequentation-rarity balance network. arXiv preprint arXiv:2603.29291. — [arXiv:2603.29291](https://arxiv.org/abs/2603.29291) [find](https://scholar.google.com/scholar?q=Guozhi+Qiu%2C+Zhiwei+Chen%2C+Zixu+Li%2C+Qinlei+Huang%2C+Zhiheng+Fu%2C+Xuemeng+Song%2C+and+Yupeng+Hu%2E+2026%2E+Melt%3A+Improve+composed+image+retrieval+via+the+modification+frequentation%2Drarity+balance+network%2E+arXiv+p)
23. Yan Rong, Jinting Wang, Shan Yang, Guangzhi Lei, and Li Liu. 2025. Audiogenie: A training-free multi-agent framework for diverse multimodality-to-multiaudio generation. arXiv preprint arXiv:2505.22053. — [arXiv:2505.22053](https://arxiv.org/abs/2505.22053) [find](https://scholar.google.com/scholar?q=Yan+Rong%2C+Jinting+Wang%2C+Shan+Yang%2C+Guangzhi+Lei%2C+and+Li+Liu%2E+2025%2E+Audiogenie%3A+A+training%2Dfree+multi%2Dagent+framework+for+diverse+multimodality%2Dto%2Dmultiaudio+generation%2E+arXiv+preprint+arXiv%3A2505%2E22053)
24. Jiajun Shi, Jian Yang, Jiaheng Liu, Xingyuan Bu, Jiangjie Chen, Junting Zhou, Kaijing Ma, Zhoufutu Wen, Bingli Wang, Yancheng He, Liang Song, Hualei Zhu, Shilong Li, Xingjian Wang, Wei Zhang, Ruibin Yuan, Yifan Yao, Wenjun Yang, Yunli Wang, and 10 others. 2025. Korgym: A dynamic game platform for ll… — [arXiv:2505.14552](https://arxiv.org/abs/2505.14552) [find](https://scholar.google.com/scholar?q=Jiajun+Shi%2C+Jian+Yang%2C+Jiaheng+Liu%2C+Xingyuan+Bu%2C+Jiangjie+Chen%2C+Junting+Zhou%2C+Kaijing+Ma%2C+Zhoufutu+Wen%2C+Bingli+Wang%2C+Yancheng+He%2C+Liang+Song%2C+Hualei+Zhu%2C+Shilong+Li%2C+Xingjian+Wang%2C+Wei+Zhang%2C+Ruibin+Y)
25. Huajie Tan, Yuheng Ji, Xiaoshuai Hao, Minglan Lin, Pengwei Wang, Zhongyuan Wang, and Shanghang Zhang. 2025. Reason-rft: Reinforcement fine-tuning for visual reasoning. Preprint, arXiv:2503.20752. — [arXiv:2503.20752](https://arxiv.org/abs/2503.20752) [find](https://scholar.google.com/scholar?q=Huajie+Tan%2C+Yuheng+Ji%2C+Xiaoshuai+Hao%2C+Minglan+Lin%2C+Pengwei+Wang%2C+Zhongyuan+Wang%2C+and+Shanghang+Zhang%2E+2025%2E+Reason%2Drft%3A+Reinforcement+fine%2Dtuning+for+visual+reasoning%2E+Preprint%2C+arXiv%3A2503%2E20752%2E+%E2%80%94+%5Ba)
26. Shuo Tang, Xianghe Pang, Zexi Liu, Bohan Tang, Rui Ye, Tian Jin, Xiaowen Dong, Yanfeng Wang, and Siheng Chen. 2025. [Synthesizing post-training data for LLMs through multi-agent simulation](https://md.research.elamur.ai/free/en/papers/tang-2025-synthesizing-post-training-data-llms/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
27. Yaoting Wang, Shengqiong Wu, Yuecheng Zhang, Shuicheng Yan, Ziwei Liu, Jiebo Luo, and Hao Fei. 2025. Multimodal chain-of-thought reasoning: A comprehensive survey. Preprint, arXiv:2503.12605. — [arXiv:2503.12605](https://arxiv.org/abs/2503.12605) [find](https://scholar.google.com/scholar?q=Yaoting+Wang%2C+Shengqiong+Wu%2C+Yuecheng+Zhang%2C+Shuicheng+Yan%2C+Ziwei+Liu%2C+Jiebo+Luo%2C+and+Hao+Fei%2E+2025%2E+Multimodal+chain%2Dof%2Dthought+reasoning%3A+A+comprehensive+survey%2E+Preprint%2C+arXiv%3A2503%2E12605%2E+%E2%80%94+%5BarXiv)
28. Zhenyu Wang, Aoxue Li, Zhenguo Li, and Xihui Liu. 2024. Genartist: Multimodal llm as an agent for unified image generation and editing. Advances in Neural Information Processing Systems, 37:128374– 128395. [find](https://scholar.google.com/scholar?q=Zhenyu+Wang%2C+Aoxue+Li%2C+Zhenguo+Li%2C+and+Xihui+Liu%2E+2024%2E+Genartist%3A+Multimodal+llm+as+an+agent+for+unified+image+generation+and+editing%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A128374%E2%80%93+12)
29. Chenxi Whitehouse, Tianlu Wang, Ping Yu, Xian Li, Jason Weston, Ilia Kulikov, and Swarnadeep Saha. 2025. J1: Incentivizing thinking in llm-as-a-judge via reinforcement learning. Preprint, arXiv:2505.10320. — [arXiv:2505.10320](https://arxiv.org/abs/2505.10320) [find](https://scholar.google.com/scholar?q=Chenxi+Whitehouse%2C+Tianlu+Wang%2C+Ping+Yu%2C+Xian+Li%2C+Jason+Weston%2C+Ilia+Kulikov%2C+and+Swarnadeep+Saha%2E+2025%2E+J1%3A+Incentivizing+thinking+in+llm%2Das%2Da%2Djudge+via+reinforcement+learning%2E+Preprint%2C+arXiv%3A2505%2E1)
30. Junfei Wu, Jian Guan, Kaituo Feng, Qiang Liu, Shu Wu, Liang Wang, Wei Wu, and Tieniu Tan. 2025. Reinforcing spatial reasoning in vision-language models with interwoven thinking and visual drawing. Preprint, arXiv:2506.09965. 2025c. ga − s 3 : Comprehensive social network simulation with group agents… [find](https://scholar.google.com/scholar?q=Junfei+Wu%2C+Jian+Guan%2C+Kaituo+Feng%2C+Qiang+Liu%2C+Shu+Wu%2C+Liang+Wang%2C+Wei+Wu%2C+and+Tieniu+Tan%2E+2025%2E+Reinforcing+spatial+reasoning+in+vision%2Dlanguage+models+with+interwoven+thinking+and+visual+drawing%2E+Pre)
31. Shuang Wu, Liwen Zhu, Tao Yang, Shiwei Xu, Qiang Fu, Yang Wei, and Haobo Fu. 2024. Enhance reasoning for large language models in the game werewolf. Preprint, arXiv:2402.02330. — [arXiv:2402.02330](https://arxiv.org/abs/2402.02330) [find](https://scholar.google.com/scholar?q=Shuang+Wu%2C+Liwen+Zhu%2C+Tao+Yang%2C+Shiwei+Xu%2C+Qiang+Fu%2C+Yang+Wei%2C+and+Haobo+Fu%2E+2024%2E+Enhance+reasoning+for+large+language+models+in+the+game+werewolf%2E+Preprint%2C+arXiv%3A2402%2E02330%2E+%E2%80%94+%5BarXiv%3A2402%2E02330%5D%28ht)
32. Yuyao Zhang, Jinghao Li, and Yu-Wing Tai. 2025d. Layercraft: Enhancing text-to-image generation with cot reasoning and layered object integration. arXiv preprint arXiv:2504.00010. — [arXiv:2504.00010](https://arxiv.org/abs/2504.00010) [find](https://scholar.google.com/scholar?q=Yuyao+Zhang%2C+Jinghao+Li%2C+and+Yu%2DWing+Tai%2E+2025d%2E+Layercraft%3A+Enhancing+text%2Dto%2Dimage+generation+with+cot+reasoning+and+layered+object+integration%2E+arXiv+preprint+arXiv%3A2504%2E00010%2E+%E2%80%94+%5BarXiv%3A2504%2E00010%5D)
33. Junlin Xie, Ruifei Zhang, Zhihong Chen, Xiang Wan, and Guanbin Li. 2024. Whodunitbench: Evaluating large multimodal agents via murder mystery games. Advances in Neural Information Processing Systems, 37:86655–86687. [find](https://scholar.google.com/scholar?q=Junlin+Xie%2C+Ruifei+Zhang%2C+Zhihong+Chen%2C+Xiang+Wan%2C+and+Guanbin+Li%2E+2024%2E+Whodunitbench%3A+Evaluating+large+multimodal+agents+via+murder+mystery+games%2E+Advances+in+Neural+Information+Processing+Systems%2C+)
34. Zheng Zhang, Nuoqian Xiao, Qi Chai, Deheng Ye, and Hao Wang. 2025e. Multimind: Enhancing werewolf agents with multimodal reasoning and theory of mind. arXiv preprint arXiv:2504.18039. — [arXiv:2504.18039](https://arxiv.org/abs/2504.18039) [find](https://scholar.google.com/scholar?q=Zheng+Zhang%2C+Nuoqian+Xiao%2C+Qi+Chai%2C+Deheng+Ye%2C+and+Hao+Wang%2E+2025e%2E+Multimind%3A+Enhancing+werewolf+agents+with+multimodal+reasoning+and+theory+of+mind%2E+arXiv+preprint+arXiv%3A2504%2E18039%2E+%E2%80%94+%5BarXiv%3A2504%2E18)
35. Zelai Xu, Zhexuan Xu, Xiangmin Yi, Huining Yuan, Xinlei Chen, Yi Wu, Chao Yu, and Yu Wang. 2025a. Vs-bench: Evaluating vlms for strategic reasoning and decision-making in multi-agent environments. Preprint, arXiv:2506.02387. — [arXiv:2506.02387](https://arxiv.org/abs/2506.02387) [find](https://scholar.google.com/scholar?q=Zelai+Xu%2C+Zhexuan+Xu%2C+Xiangmin+Yi%2C+Huining+Yuan%2C+Xinlei+Chen%2C+Yi+Wu%2C+Chao+Yu%2C+and+Yu+Wang%2E+2025a%2E+Vs%2Dbench%3A+Evaluating+vlms+for+strategic+reasoning+and+decision%2Dmaking+in+multi%2Dagent+environments%2E+Pre)
36. Zixiang Xu, Yanbo Wang, Yue Huang, Jiayi Ye, Haomin Zhuang, Zirui Song, Lang Gao, Chenxi Wang, Zhaorun Chen, Yujun Zhou, Sixian Li, Wang Pan, Yue Zhao, Jieyu Zhao, Xiangliang Zhang, and Xiuying Chen. 2025b. Socialmaze: A benchmark for evaluating social reasoning in large language models. Preprint, a… [find](https://scholar.google.com/scholar?q=Zixiang+Xu%2C+Yanbo+Wang%2C+Yue+Huang%2C+Jiayi+Ye%2C+Haomin+Zhuang%2C+Zirui+Song%2C+Lang+Gao%2C+Chenxi+Wang%2C+Zhaorun+Chen%2C+Yujun+Zhou%2C+Sixian+Li%2C+Wang+Pan%2C+Yue+Zhao%2C+Jieyu+Zhao%2C+Xiangliang+Zhang%2C+and+Xiuying+Chen%2E+)
37. Lianghui Zhu, Xinggang Wang, and Xinlong Wang. 2023. [Judgelm: Fine-tuned large language models are scalable judges](https://md.research.elamur.ai/free/en/papers/zhu-2023-judgelm-fine-tuned-large-language/).
38. Qinglin Zhu, Runcong Zhao, Bin Liang, Jinhua Du, Lin Gui, and Yulan He. 2025. Player*: Enhancing llm-based multi-agent communication and interaction in murder mystery games. Preprint, arXiv:2404.17662. — [arXiv:2404.17662](https://arxiv.org/abs/2404.17662) [find](https://scholar.google.com/scholar?q=Qinglin+Zhu%2C+Runcong+Zhao%2C+Bin+Liang%2C+Jinhua+Du%2C+Lin+Gui%2C+and+Yulan+He%2E+2025%2E+Player%2A%3A+Enhancing+llm%2Dbased+multi%2Dagent+communication+and+interaction+in+murder+mystery+games%2E+Preprint%2C+arXiv%3A2404%2E17662)
39. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). arXiv preprint arXiv:1809.09600.
40. Mingyu Zhang, Zixu Li, Zhiwei Chen, Zhiheng Fu, Xiaowei Zhu, Jiajia Nie, Yinwei Wei, and Yupeng Hu. 2026a. Hint: Composed image retrieval with dual-path compositional contextualized network. arXiv preprint arXiv:2603.26341. — [arXiv:2603.26341](https://arxiv.org/abs/2603.26341) [find](https://scholar.google.com/scholar?q=Mingyu+Zhang%2C+Zixu+Li%2C+Zhiwei+Chen%2C+Zhiheng+Fu%2C+Xiaowei+Zhu%2C+Jiajia+Nie%2C+Yinwei+Wei%2C+and+Yupeng+Hu%2E+2026a%2E+Hint%3A+Composed+image+retrieval+with+dual%2Dpath+compositional+contextualized+network%2E+arXiv+pre)
41. Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, and Yongbin Li. 2026b. [Expseek: Self-triggered experience seeking for web agents](https://md.research.elamur.ai/free/en/papers/zhang-2026-expseek-self-triggered-experience-seeking/). Preprint, arXiv:2601.08605.
42. Xiaojiang Zhang, Jinghui Wang, Zifei Cheng, Wenhao Zhuang, Zheng Lin, Minglei Zhang, Shaojie Wang, Yinghan Cui, Chao Wang, Junyi Peng, Shimiao Jiang, Shiqi Kuang, Shouyu Yin, Chaohang Wen, Haotian Zhang, Bin Chen, and Bing Yu. 2025a. Srpo: A cross-domain implementation of large-scale reinforcement l… — [arXiv:2504.14286](https://arxiv.org/abs/2504.14286) [find](https://scholar.google.com/scholar?q=Xiaojiang+Zhang%2C+Jinghui+Wang%2C+Zifei+Cheng%2C+Wenhao+Zhuang%2C+Zheng+Lin%2C+Minglei+Zhang%2C+Shaojie+Wang%2C+Yinghan+Cui%2C+Chao+Wang%2C+Junyi+Peng%2C+Shimiao+Jiang%2C+Shiqi+Kuang%2C+Shouyu+Yin%2C+Chaohang+Wen%2C+Haotian+Zha)
43. Xinjie Zhang, Jintao Guo, Shanshan Zhao, Minghao Fu, Lunhao Duan, Guo-Hua Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, and Kaifu Zhang. 2025b. Unified multimodal understanding and generation models: Advances, challenges, and opportunities. arXiv preprint arXiv:2505.02567. — [arXiv:2505.02567](https://arxiv.org/abs/2505.02567) [find](https://scholar.google.com/scholar?q=Xinjie+Zhang%2C+Jintao+Guo%2C+Shanshan+Zhao%2C+Minghao+Fu%2C+Lunhao+Duan%2C+Guo%2DHua+Wang%2C+Qing%2DGuo+Chen%2C+Zhao+Xu%2C+Weihua+Luo%2C+and+Kaifu+Zhang%2E+2025b%2E+Unified+multimodal+understanding+and+generation+models%3A+Adva)
44. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. [find](https://scholar.google.com/scholar?q=Yunyao+Zhang%2C+Zikai+Song%2C+Hang+Zhou%2C+Wenfeng+Ren%2C+Yi%2DPing+Phoebe+Chen%2C+Junqing+Yu%2C+and+Wei+Yang%2E)

*Updated 1 November 2026*