---
title: "Conflict-Aware Memory for Embodied Agents: Enhancing Vector"
description: "The authors adapt data dependencies from relational data cleaning and propose Conflict Detection Rules (CDRs). 66 references."
authors: ["Kexin Ma", "Haotian Wang", "Shenglin Chen", "Yishuai Cai", "Huangyuyu", "Ruochun Jin"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1306/"
doi: "10.18653/v1/2026.acl-long.1306"
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/ma-2026-conflict-aware-memory-embodied-agents/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ma-2026-conflict-aware-memory-embodied-agents/)

[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/25/) / Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules

# Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules

**Authors:** Kexin Ma, [Haotian Wang](https://md.research.elamur.ai/free/en/authors/haotian-wang/), Shenglin Chen, Yishuai Cai, Huangyuyu and Ruochun Jin · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1306/) · [PDF](https://aclanthology.org/2026.acl-long.1306.pdf) · [DOI 10.18653/v1/2026.acl-long.1306](https://doi.org/10.18653/v1/2026.acl-long.1306) · [OpenAlex](https://openalex.org/W7166821830)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

Embodied agents increasingly use LLM planners that draw on a vector memory of past instructions and observations. Embedding-based retrieval, however, often fails to separate commands that look nearly identical but require opposite or different actions (switching a light on versus off, for example), and it also struggles with near-duplicate images. When such clashing neighbours are fed to the planner, the robot can carry out the wrong action.

The authors adapt data dependencies from relational data cleaning and propose Conflict Detection Rules (CDRs). These rules split each sentence into object–operation pairs, compare those components, and combine the comparison with a vector-similarity threshold. When two entries are highly similar but disagree on the action or the object, the rules flag them as conflicting. CDRs run after retrieval: they discard conflicting contexts and trim the matching entries from the vector index, so the memory gets cleaner over time.

Planners using CDRs improved on a basic LLM planner, with average gains of 15.25% for GA and 14.25% for IA. They also outperform an LLM-based conflict filter. The work shows that memory quality strongly affects plan reliability, and it offers a fix that can be attached to any planner.

## Key points

- **Scale of the problem:** after building the knowledge base, roughly 1.8 of the top-10 retrieved commands per query conflicted with the request.
- **Gains over baselines:** CDRs beat the basic planner by 15.25% GA and 14.25% IA on average. Over a normal memory-enhanced planner, the gains were 14.00% GA and 11.25% IA.
- **Robustness to noise:** on Café_t with gpt-3.5-turbo, GA dropped from 100% to 92% under mixed irrelevant and contradictory noise for CDRs. Plain RAG fell from 78% to 63% under the same conditions.
- **Comparison with other RAG methods:** CDRs consistently improved accuracy when compared with SelfRAG and SuRe. Weaker models such as Llama2-7b benefited most, gaining up to +20%.
- **Deployment and code:** the workflow was tested in Café, Canteen, Kitchen and Lounge scenarios. It was deployed with OBTEA as a humanoid waiter robot in the MO-vln simulator, and the code is at github.com/makexine/CDRs.

*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

- [National University of Defense Technology](https://md.research.elamur.ai/free/en/universities/national-university-of-defense-technology/) — University, Changsha, China · 10 works · 931 citations

📚 Shelves (6): [🖥️ 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 133 works · [⚙️ Control and Systems Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/control-and-systems-engineering/) · 45 works

## Cite

Cite as: Kexin Ma, Haotian Wang, Shenglin Chen, Yishuai Cai, Huangyuyu and Ruochun Jin. 2026. Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules. 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.

```bibtex
@inproceedings{ma2026conflict,
  title = {{Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules}},
  author = {Kexin Ma, Haotian Wang, Shenglin Chen, Yishuai Cai, Huangyuyu and Ruochun Jin},
  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.1306},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1306}
}
```

- [← previous Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection](https://md.research.elamur.ai/free/en/papers/selvaganapathy-2026-confident-calibrated-or-complicit-safety/)
- [next → ConGA: Guidelines for Contextual Gender Annotation. a Framework for Annotating Gender in Machine Translation](https://md.research.elamur.ai/free/en/papers/rescigno-2026-conga-guidelines-contextual-gender-annotation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/)

## References

66 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Serge Abiteboul, Richard Hull, and Victor Vianu. 1994. Foundations of databases. [find](https://scholar.google.com/scholar?q=Serge+Abiteboul%2C+Richard+Hull%2C+and+Victor+Vianu%2E+1994%2E+Foundations+of+databases%2E)
2. Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alexander Herzog, Daniel Ho, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Eric Jang, Rosario M Jauregui Ruano, Kyle Jeffrey, Sally Jesmonth, and 24 other… — [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://md.research.elamur.ai/free/en/papers/ahn-2022-i-i-say-grounding-language/)
3. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Merouane Debbah, Etienne Goffinet, Daniel Heslow, Julien Launay, Quentin Malartic, Badreddine Noune, Baptiste Pannier, and Guilherme Penedo. 2023. Falcon-40B: an open large language model with state-of-t… [find](https://scholar.google.com/scholar?q=Ebtesam+Almazrouei%2C+Hamza+Alobeidli%2C+Abdulaziz+Alshamsi%2C+Alessandro+Cappelli%2C+Ruxandra+Cojocaru%2C+Merouane+Debbah%2C+Etienne+Goffinet%2C+Daniel+Heslow%2C+Julien+Launay%2C+Quentin+Malartic%2C+Badreddine+Noune%2C+Ba)
4. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/).
5. Shi-Kuo Chang, Vincenzo Deufemia, Giuseppe Polese, and Mario Vacca. 2007. A normalization framework for multimedia databases. IEEE Transactions on Knowledge and Data Engineering, 19:1666–1679. [find](https://scholar.google.com/scholar?q=Shi%2DKuo+Chang%2C+Vincenzo+Deufemia%2C+Giuseppe+Polese%2C+and+Mario+Vacca%2E+2007%2E+A+normalization+framework+for+multimedia+databases%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+19%3A1666%E2%80%931679%2E)
6. Xinglin Chen, Yishuai Cai, Yunxin Mao, Minglong Li, Wenjing Yang, Weixia Xu, and Ji Wang. 2024. Integrating intent understanding and optimal behavior planning for behavior tree generation from human instructions. ArXiv, abs/2405.07474. — [arXiv:2405.07474](https://arxiv.org/abs/2405.07474) [find](https://scholar.google.com/scholar?q=Xinglin+Chen%2C+Yishuai+Cai%2C+Yunxin+Mao%2C+Minglong+Li%2C+Wenjing+Yang%2C+Weixia+Xu%2C+and+Ji+Wang%2E+2024%2E+Integrating+intent+understanding+and+optimal+behavior+planning+for+behavior+tree+generation+from+human+i)
7. Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, and Yunhong Wang. 2026. [Mem 2 evolve: Towards self-evolving agents via co-evolutionary capability expansion and experience distillation](https://md.research.elamur.ai/free/en/papers/cheng-2026-mem-2-evolve-self-evolving/). Preprint, arXiv:2604.10923.
8. E. F. Codd. 1971. Further normalization of the data base relational model. Research Report / RJ / IBM / San Jose, California, RJ909. [find](https://scholar.google.com/scholar?q=E%2E+F%2E+Codd%2E+1971%2E+Further+normalization+of+the+data+base+relational+model%2E+Research+Report+%2F+RJ+%2F+IBM+%2F+San+Jose%2C+California%2C+RJ909%2E)
9. XTuner Contributors. 2023. Xtuner: A toolkit for efficiently fine-tuning llm. [https://github.com/](https://github.com/) InternLM/xtuner. [↗](https://github.com/)
10. Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, and Hervé Jégou. 2024. [The faiss library](https://md.research.elamur.ai/free/en/papers/douze-2024-faiss-library/).
11. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
12. Wenfei Fan, Hong Gao, Xibei Jia, Jianzhong Li, and Shuai Ma. 2011. Dynamic constraints for record matching. The VLDB Journal, 20:495–520. [find](https://scholar.google.com/scholar?q=Wenfei+Fan%2C+Hong+Gao%2C+Xibei+Jia%2C+Jianzhong+Li%2C+and+Shuai+Ma%2E+2011%2E+Dynamic+constraints+for+record+matching%2E+The+VLDB+Journal%2C+20%3A495%E2%80%93520%2E)
13. Wenfei Fan and Floris Geerts. 2011. Uniform dependency language for improving data quality. IEEE Data Eng. Bull., 34:34–42. [find](https://scholar.google.com/scholar?q=Wenfei+Fan+and+Floris+Geerts%2E+2011%2E+Uniform+dependency+language+for+improving+data+quality%2E+IEEE+Data+Eng%2E+Bull%2E%2C+34%3A34%E2%80%9342%2E)
14. Wenfei Fan, Floris Geerts, Xibei Jia, and Anastasios Kementsietsidis. 2008. Conditional functional dependencies for capturing data inconsistencies. ACM Trans. Database Syst., 33:6:1–6:48. [find](https://scholar.google.com/scholar?q=Wenfei+Fan%2C+Floris+Geerts%2C+Xibei+Jia%2C+and+Anastasios+Kementsietsidis%2E+2008%2E+Conditional+functional+dependencies+for+capturing+data+inconsistencies%2E+ACM+Trans%2E+Database+Syst%2E%2C+33%3A6%3A1%E2%80%936%3A48%2E)
15. Zhen Fang, Zhuoyang Liu, Jiaming Liu, Hao Chen, Yu Zeng, Shiting Huang, Zehui Chen, Lin Chen, Shanghang Zhang, and Feng Zhao. 2025. Dualvla: Building a generalizable embodied agent via partial decoupling of reasoning and action. arXiv preprint arXiv:2511.22134. — [arXiv:2511.22134](https://arxiv.org/abs/2511.22134) [find](https://scholar.google.com/scholar?q=Zhen+Fang%2C+Zhuoyang+Liu%2C+Jiaming+Liu%2C+Hao+Chen%2C+Yu+Zeng%2C+Shiting+Huang%2C+Zehui+Chen%2C+Lin+Chen%2C+Shanghang+Zhang%2C+and+Feng+Zhao%2E+2025%2E+Dualvla%3A+Building+a+generalizable+embodied+agent+via+partial+decoupl)
16. Junan Hu, Shudan Guo, Wenqi Liu, Jianhua Yin, and Yinwei Wei. 2026. Context-agent: Dynamic discourse trees for non-linear dialogue. arXiv preprint arXiv:2604.05552. [find](https://scholar.google.com/scholar?q=Junan+Hu%2C+Shudan+Guo%2C+Wenqi+Liu%2C+Jianhua+Yin%2C+and+Yinwei+Wei%2E+2026%2E+Context%2Dagent%3A+Dynamic+discourse+trees+for+non%2Dlinear+dialogue%2E+arXiv+preprint+arXiv%3A2604%2E05552%2E)
17. Chenguang Huang, Oier Mees, Andy Zeng, and Wolfram Burgard. 2023. Visual language maps for robot navigation. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 10608– 10615. IEEE. [find](https://scholar.google.com/scholar?q=Chenguang+Huang%2C+Oier+Mees%2C+Andy+Zeng%2C+and+Wolfram+Burgard%2E+2023%2E+Visual+language+maps+for+robot+navigation%2E+In+2023+IEEE+International+Conference+on+Robotics+and+Automation+%28ICRA%29%2C+pages+10608%E2%80%93+10615)
18. Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022. [Language models as zero-shot planners: Extracting actionable knowledge for embodied agents](https://md.research.elamur.ai/free/en/papers/huang-2022-language-models-zero-shot-planners/). In Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 911…
19. Yu Huang, Ziji Wu, Kexin Ma, and Ji Wang. 2025. Differentiable synthesis of behavior tree architectures and execution nodes. In International Conference on Neuro-symbolic Systems, 28-30 May 2025, University of Pennsylvania, Philadelphia, Pennsylvania, USA, Proceedings of Machine Learning Research, p… [find](https://scholar.google.com/scholar?q=Yu+Huang%2C+Ziji+Wu%2C+Kexin+Ma%2C+and+Ji+Wang%2E+2025%2E+Differentiable+synthesis+of+behavior+tree+architectures+and+execution+nodes%2E+In+International+Conference+on+Neuro%2Dsymbolic+Systems%2C+28%2D30+May+2025%2C+Univ)
20. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. [Unsupervised dense information retrieval with contrastive learning](https://md.research.elamur.ai/free/en/papers/izacard-2021-unsupervised-dense-information-retrieval-contrastive/).
21. Trans. Mach. Learn. Res., 2022. [find](https://scholar.google.com/scholar?q=Trans%2E+Mach%2E+Learn%2E+Res%2E%2C+2022%2E)
22. Masoud Jafaripour, Shadan Golestan, Shotaro Miwa, Yoshihiro Mitsuka, and Osmar Zaiane. 2025. Adaptive iterative feedback prompting for obstacle-aware path planning via llms. In AAAI 2025 Workshop LM4Plan. [find](https://scholar.google.com/scholar?q=Masoud+Jafaripour%2C+Shadan+Golestan%2C+Shotaro+Miwa%2C+Yoshihiro+Mitsuka%2C+and+Osmar+Zaiane%2E+2025%2E+Adaptive+iterative+feedback+prompting+for+obstacle%2Daware+path+planning+via+llms%2E+In+AAAI+2025+Workshop+LM4P)
23. Masoud Jafaripour, Shadan Golestan, Shotaro Miwa, Yoshihiro Mitsuka, and Osmar R. Zaiane. Adaptive iterative feedback prompting for obstacle-aware path planning via llms. [find](https://scholar.google.com/scholar?q=Masoud+Jafaripour%2C+Shadan+Golestan%2C+Shotaro+Miwa%2C+Yoshihiro+Mitsuka%2C+and+Osmar+R%2E+Zaiane%2E+Adaptive+iterative+feedback+prompting+for+obstacle%2Daware+path+planning+via+llms%2E)
24. Reza Karegar, Parke Godfrey, Lukasz Golab, Mehdi Kargar, Divesh Srivastava, and Jaroslaw Szlichta. 2021. Efficient discovery of approximate order dependencies. In Proceedings of the 24th International Conference on Extending Database Technology, EDBT 2021, Nicosia, Cyprus, March 23 - 26, 2021, pages… [find](https://scholar.google.com/scholar?q=Reza+Karegar%2C+Parke+Godfrey%2C+Lukasz+Golab%2C+Mehdi+Kargar%2C+Divesh+Srivastava%2C+and+Jaroslaw+Szlichta%2E+2021%2E+Efficient+discovery+of+approximate+order+dependencies%2E+In+Proceedings+of+the+24th+International)
25. Jaehyung Kim. 2024. Sure: Summarizing retrievals using answer candidates for open-domain qa of llms. [find](https://scholar.google.com/scholar?q=Jaehyung+Kim%2E+2024%2E+Sure%3A+Summarizing+retrievals+using+answer+candidates+for+open%2Ddomain+qa+of+llms%2E)
26. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, and 1 others. 2023. Bloom: A 176b-parameter open-access multilingual language model. [find](https://scholar.google.com/scholar?q=Teven+Le+Scao%2C+Angela+Fan%2C+Christopher+Akiki%2C+Ellie+Pavlick%2C+Suzana+Ilic%CC%81%2C+Daniel+Hesslow%2C+Roman+Castagn%C3%A9%2C+Alexandra+Sasha+Luccioni%2C+Fran%C3%A7ois+Yvon%2C+Matthias+Gall%C3%A9%2C+and+1+others%2E+2023%2E+Bloom%3A+A+176b%2Dpa)
27. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. [BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages…
28. Xiwen Liang, Liang Ma, Shanshan Guo, Jianhua Han, Hang Xu, Shikui Ma, and Xiaodan Liang. 2023. Mo-vln: A multi-task benchmark for open-set zero-shot vision-and-language navigation. arXiv preprint arXiv:2306.10322. — [arXiv:2306.10322](https://arxiv.org/abs/2306.10322) [find](https://scholar.google.com/scholar?q=Xiwen+Liang%2C+Liang+Ma%2C+Shanshan+Guo%2C+Jianhua+Han%2C+Hang+Xu%2C+Shikui+Ma%2C+and+Xiaodan+Liang%2E+2023%2E+Mo%2Dvln%3A+A+multi%2Dtask+benchmark+for+open%2Dset+zero%2Dshot+vision%2Dand%2Dlanguage+navigation%2E+arXiv+preprint+arXi)
29. Jiaye Lin, Yifu Guo, Yuzhen Han, Sen Hu, Ziyi Ni, Licheng Wang, Mingguang Chen, Hongzhang Liu, Ronghao Chen, Yangfan He, and 1 others. 2025. Seagent: Self-evolution trajectory optimization in multi-step reasoning with llm-based agents. arXiv preprint arXiv:2508.02085. — [arXiv:2508.02085](https://arxiv.org/abs/2508.02085) [find](https://scholar.google.com/scholar?q=Jiaye+Lin%2C+Yifu+Guo%2C+Yuzhen+Han%2C+Sen+Hu%2C+Ziyi+Ni%2C+Licheng+Wang%2C+Mingguang+Chen%2C+Hongzhang+Liu%2C+Ronghao+Chen%2C+Yangfan+He%2C+and+1+others%2E+2025%2E+Seagent%3A+Self%2Devolution+trajectory+optimization+in+multi%2Dst)
30. 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](https://md.research.elamur.ai/free/en/papers/liu-2023-llm-p-empowering-large-language/). arXiv preprint arXiv:2304.11477.
31. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2023b. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173.
32. Artem Lykov, Maria Dronova, Nikolay Naglov, Mikhail Litvinov, Sergei Satsevich, Artem Bazhenov, Vladimir Berman, Aleksei Shcherbak, and Dzmitry Tsetserukou. 2023. Llm-mars: Large language model for behavior tree generation and nlp-enhanced dialogue in multi-agent robot systems. ArXiv, abs/2312.09348… — [arXiv:2312.09348](https://arxiv.org/abs/2312.09348) [find](https://scholar.google.com/scholar?q=Artem+Lykov%2C+Maria+Dronova%2C+Nikolay+Naglov%2C+Mikhail+Litvinov%2C+Sergei+Satsevich%2C+Artem+Bazhenov%2C+Vladimir+Berman%2C+Aleksei+Shcherbak%2C+and+Dzmitry+Tsetserukou%2E+2023%2E+Llm%2Dmars%3A+Large+language+model+for+be)
33. Artem Lykov and Dzmitry Tsetserukou. 2023. Llm-brain: Ai-driven fast generation of robot behaviour tree based on large language model. ArXiv, abs/2305.19352. — [arXiv:2305.19352](https://arxiv.org/abs/2305.19352) [find](https://scholar.google.com/scholar?q=Artem+Lykov+and+Dzmitry+Tsetserukou%2E+2023%2E+Llm%2Dbrain%3A+Ai%2Ddriven+fast+generation+of+robot+behaviour+tree+based+on+large+language+model%2E+ArXiv%2C+abs%2F2305%2E19352%2E+%E2%80%94+%5BarXiv%3A2305%2E19352%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs)
34. Kexin Ma, Ruochun Jin, Xi Wang, Huan Chen, Jing Ren, and Yuhua Tang. 2024. Context-driven index trimming: A data quality perspective to enhancing precision of ralms. [find](https://scholar.google.com/scholar?q=Kexin+Ma%2C+Ruochun+Jin%2C+Xi+Wang%2C+Huan+Chen%2C+Jing+Ren%2C+and+Yuhua+Tang%2E+2024%2E+Context%2Ddriven+index+trimming%3A+A+data+quality+perspective+to+enhancing+precision+of+ralms%2E)
35. Kexin Ma, Bojun Li, Yuhua Tang, Liting Sun, and Ruochun Jin. 2026a. Cast: Character-and-scene episodic memory for agents. Preprint, arXiv:2602.06051. — [arXiv:2602.06051](https://arxiv.org/abs/2602.06051) [find](https://scholar.google.com/scholar?q=Kexin+Ma%2C+Bojun+Li%2C+Yuhua+Tang%2C+Liting+Sun%2C+and+Ruochun+Jin%2E+2026a%2E+Cast%3A+Character%2Dand%2Dscene+episodic+memory+for+agents%2E+Preprint%2C+arXiv%3A2602%2E06051%2E+%E2%80%94+%5BarXiv%3A2602%2E06051%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2602%2E06)
36. Xiaoxu Ma, Xiangbo Zhang, and Zhenyu Weng. 2026b. [Stable and explainable personality trait evaluation in large language models with internal activations](https://md.research.elamur.ai/free/en/papers/ma-2026-stable-explainable-personality-trait-evaluation/). Preprint, arXiv:2601.09833.
37. Yury Malkov, Alexander Ponomarenko, Andrey Logvi-nov, and Vladimir Krylov. 2014. Approximate nearest neighbor algorithm based on navigable small world graphs. Information Systems, 45:61–68. [find](https://scholar.google.com/scholar?q=Yury+Malkov%2C+Alexander+Ponomarenko%2C+Andrey+Logvi%2Dnov%2C+and+Vladimir+Krylov%2E+2014%2E+Approximate+nearest+neighbor+algorithm+based+on+navigable+small+world+graphs%2E+Information+Systems%2C+45%3A61%E2%80%9368%2E)
38. Yury Malkov and Dmitry A. Yashunin. 2016. [Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs](https://md.research.elamur.ai/free/en/papers/malkov-2016-efficient-robust-approximate-nearest-neighbor/). IEEE Transactions on Pattern Analysis and Machine Intelligence, 42:824–836.
39. Peiyang Liu, Ziqiang Cui, Di Liang, and Wei Ye. 2025a. Who stole your data? a method for detecting unauthorized rag theft. arXiv preprint arXiv:2510.07728. — [arXiv:2510.07728](https://arxiv.org/abs/2510.07728) [find](https://scholar.google.com/scholar?q=Peiyang+Liu%2C+Ziqiang+Cui%2C+Di+Liang%2C+and+Wei+Ye%2E+2025a%2E+Who+stole+your+data%3F+a+method+for+detecting+unauthorized+rag+theft%2E+arXiv+preprint+arXiv%3A2510%2E07728%2E+%E2%80%94+%5BarXiv%3A2510%2E07728%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2)
40. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, and 1 others. 2022. [Crosslingual generalization through multitask finetuning](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-crosslingual-generalization-through-multitask-finetuning/). arXiv preprint arXiv:2211.01786.
41. Peiyang Liu, Xi Wang, Ziqiang Cui, and Wei Ye. 2025b. Queries are not alone: Clustering text embeddings for video search. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 874– 883. [find](https://scholar.google.com/scholar?q=Peiyang+Liu%2C+Xi+Wang%2C+Ziqiang+Cui%2C+and+Wei+Ye%2E+2025b%2E+Queries+are+not+alone%3A+Clustering+text+embeddings+for+video+search%2E+In+Proceedings+of+the+48th+International+ACM+SIGIR+Conference+on+Research+and+)
42. 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](https://scholar.google.com/scholar?q=Xavier+Puig%2C+Kevin+Ra%2C+Marko+Boben%2C+Jiaman+Li%2C+Tingwu+Wang%2C+Sanja+Fidler%2C+and+Antonio+Torralba%2E+2018%2E+Virtualhome%3A+Simulating+household+activities+via+programs%2E+In+Proceedings+of+the+IEEE+conference+o)
43. Peiyang Liu, Jinyu Yang, Lin Wang, Sen Wang, Yunlai Hao, and Huihui Bai. 2023c. Retrieval-based unsupervised noisy label detection on text data. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 4099–4104. [find](https://scholar.google.com/scholar?q=Peiyang+Liu%2C+Jinyu+Yang%2C+Lin+Wang%2C+Sen+Wang%2C+Yunlai+Hao%2C+and+Huihui+Bai%2E+2023c%2E+Retrieval%2Dbased+unsupervised+noisy+label+detection+on+text+data%2E+In+Proceedings+of+the+32nd+ACM+International+Conference)
44. K. Raju and Arun Kumar Majumdar. 1988. Fuzzy functional dependencies and lossless join decomposition of fuzzy relational database systems. ACM Trans. Database Syst., 13:129–166. [find](https://scholar.google.com/scholar?q=K%2E+Raju+and+Arun+Kumar+Majumdar%2E+1988%2E+Fuzzy+functional+dependencies+and+lossless+join+decomposition+of+fuzzy+relational+database+systems%2E+ACM+Trans%2E+Database+Syst%2E%2C+13%3A129%E2%80%93166%2E)
45. Yujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, and William Yang Wang. 2022. Neuro-symbolic procedural planning with commonsense prompting. arXiv preprint arXiv:2206.02928. — [arXiv:2206.02928](https://arxiv.org/abs/2206.02928) [find](https://scholar.google.com/scholar?q=Yujie+Lu%2C+Weixi+Feng%2C+Wanrong+Zhu%2C+Wenda+Xu%2C+Xin+Eric+Wang%2C+Miguel+Eckstein%2C+and+William+Yang+Wang%2E+2022%2E+Neuro%2Dsymbolic+procedural+planning+with+commonsense+prompting%2E+arXiv+preprint+arXiv%3A2206%2E02928)
46. Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. 2020. [Alfred: A benchmark for interpreting grounded instructions for everyday tasks](https://md.research.elamur.ai/free/en/papers/shridhar-2019-alfred-benchmark-interpreting-grounded-instructions/). In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, page…
47. 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](https://md.research.elamur.ai/free/en/papers/singh-2022-progprompt-generating-situated-robot-task/). In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 1…
48. Chan Hee Song, Jiaman Wu, Clay Washington, Brian M. Sadler, Wei-Lun Chao, and Yu Su. 2022. [Llm-planner: Few-shot grounded planning for embodied agents with large language models](https://md.research.elamur.ai/free/en/papers/song-2022-llm-planner-few-shot-grounded/). 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 2986–2997.
49. Gemma Team. 2024a. Gemma. [find](https://scholar.google.com/scholar?q=Gemma+Team%2E+2024a%2E+Gemma%2E)
50. Qwen Team. 2024b. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024b%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
51. Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Daniel M. Bikel, Lukas Blecher, Cristian Cantón Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
52. Sai H Vemprala, Rogerio Bonatti, Arthur Bucker, and Ashish Kapoor. 2024. Chatgpt for robotics: Design principles and model abilities. IEEE Access. [find](https://scholar.google.com/scholar?q=Sai+H+Vemprala%2C+Rogerio+Bonatti%2C+Arthur+Bucker%2C+and+Ashish+Kapoor%2E+2024%2E+Chatgpt+for+robotics%3A+Design+principles+and+model+abilities%2E+IEEE+Access%2E)
53. Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023. [Self-knowledge guided retrieval augmentation for large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-self-knowledge-guided-retrieval-augmentation/). ArXiv, abs/2310.05002.
54. Quanting Xie, So Yeon Min, Pengliang Ji, Yue Yang, Tianyi Zhang, Kedi Xu, Aarav Bajaj, Ruslan Salakhutdinov, Matthew Johnson-Roberson, and Yonatan Bisk. 2024. Embodied-rag: General non-parametric embodied memory for retrieval and generation. arXiv preprint arXiv:2409.18313. [find](https://scholar.google.com/scholar?q=Quanting+Xie%2C+So+Yeon+Min%2C+Pengliang+Ji%2C+Yue+Yang%2C+Tianyi+Zhang%2C+Kedi+Xu%2C+Aarav+Bajaj%2C+Ruslan+Salakhutdinov%2C+Matthew+Johnson%2DRoberson%2C+and+Yonatan+Bisk%2E+2024%2E+Embodied%2Drag%3A+General+non%2Dparametric+embo)
55. Weiye Xu, Min Wang, Wengang Zhou, and Houqiang Li. 2024. P-rag: Progressive retrieval augmented generation for planning on embodied everyday task. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 6969–6978. [find](https://scholar.google.com/scholar?q=Weiye+Xu%2C+Min+Wang%2C+Wengang+Zhou%2C+and+Houqiang+Li%2E+2024%2E+P%2Drag%3A+Progressive+retrieval+augmented+generation+for+planning+on+embodied+everyday+task%2E+In+Proceedings+of+the+32nd+ACM+International+Conferen)
56. Jin Yamanaka and Takashi Kido. 2024. Evaluating large language models with rag capability: A perspective from robot behavior planning and execution. In Proceedings of the AAAI Symposium Series, volume 3, pages 452–456. [find](https://scholar.google.com/scholar?q=Jin+Yamanaka+and+Takashi+Kido%2E+2024%2E+Evaluating+large+language+models+with+rag+capability%3A+A+perspective+from+robot+behavior+planning+and+execution%2E+In+Proceedings+of+the+AAAI+Symposium+Series%2C+volume)
57. Qianyun Yang, Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, and Liqiang Nie. 2026. Stable: Efficient hybrid nearest neighbor search via magnitude-uniformity and cardinality-robustness. arXiv preprint arXiv:2604.01617. — [arXiv:2604.01617](https://arxiv.org/abs/2604.01617) [find](https://scholar.google.com/scholar?q=Qianyun+Yang%2C+Zhiwei+Chen%2C+Yupeng+Hu%2C+Zixu+Li%2C+Zhiheng+Fu%2C+and+Liqiang+Nie%2E+2026%2E+Stable%3A+Efficient+hybrid+nearest+neighbor+search+via+magnitude%2Duniformity+and+cardinality%2Drobustness%2E+arXiv+preprint+a)
58. Minjong Yoo, Jinwoo Jang, Wei-Jin Park, and Honguk Woo. 2024. Exploratory retrieval-augmented planning for continual embodied instruction following. Advances in Neural Information Processing Systems, 37:67034–67060. [find](https://scholar.google.com/scholar?q=Minjong+Yoo%2C+Jinwoo+Jang%2C+Wei%2DJin+Park%2C+and+Honguk+Woo%2E+2024%2E+Exploratory+retrieval%2Daugmented+planning+for+continual+embodied+instruction+following%2E+Advances+in+Neural+Information+Processing+Systems%2C+)
59. Ali Zare, Yulei Niu, Hammad Ayyubi, and Shih-fu Chang. 2024. Rap: Retrieval-augmented planner for adaptive procedure planning in instructional videos. In European Conference on Computer Vision, pages 410–426. Springer. [find](https://scholar.google.com/scholar?q=Ali+Zare%2C+Yulei+Niu%2C+Hammad+Ayyubi%2C+and+Shih%2Dfu+Chang%2E+2024%2E+Rap%3A+Retrieval%2Daugmented+planner+for+adaptive+procedure+planning+in+instructional+videos%2E+In+European+Conference+on+Computer+Vision%2C+pages+)
60. Yu Zeng, Wenxuan Huang, Zhen Fang, Shuang Chen, Yufan Shen, Yishuo Cai, Xiaoman Wang, Zhenfei Yin, Lin Chen, Zehui Chen, and 1 others. 2026. Vision-deepresearch benchmark: Rethinking visual and textual search for multimodal large language models. arXiv preprint arXiv:2602.02185. — [arXiv:2602.02185](https://arxiv.org/abs/2602.02185) [find](https://scholar.google.com/scholar?q=Yu+Zeng%2C+Wenxuan+Huang%2C+Zhen+Fang%2C+Shuang+Chen%2C+Yufan+Shen%2C+Yishuo+Cai%2C+Xiaoman+Wang%2C+Zhenfei+Yin%2C+Lin+Chen%2C+Zehui+Chen%2C+and+1+others%2E+2026%2E+Vision%2Ddeepresearch+benchmark%3A+Rethinking+visual+and+textua)
61. Qianchi Zhang, Hainan Zhang, Liang Pang, Yongxin Tong, Hongwei Zheng, and Zhiming Zheng. 2025. Less is more: Compact clue selection for efficient retrieval-augmented generation reasoning. arXiv preprint arXiv:2502.11811. — [arXiv:2502.11811](https://arxiv.org/abs/2502.11811) [find](https://scholar.google.com/scholar?q=Qianchi+Zhang%2C+Hainan+Zhang%2C+Liang+Pang%2C+Yongxin+Tong%2C+Hongwei+Zheng%2C+and+Zhiming+Zheng%2E+2025%2E+Less+is+more%3A+Compact+clue+selection+for+efficient+retrieval%2Daugmented+generation+reasoning%2E+arXiv+prepri)
62. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2026a. [Stable-rag: Mitigating retrieval-permutation-induced hallucinations in retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/zhang-2026-stable-rag-mitigating-retrieval-permutation/). arXiv preprint arXiv:2601.02993.
63. 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.
64. Yuanjun Zhang, Fuzel Ahamed Shaik, Suvojit Acharjee, Fahad Khalid, and Mourad Oussalah. 2026c. Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning. Reliability Engineering & System Safety, page 112674. [find](https://scholar.google.com/scholar?q=Yuanjun+Zhang%2C+Fuzel+Ahamed+Shaik%2C+Suvojit+Acharjee%2C+Fahad+Khalid%2C+and+Mourad+Oussalah%2E+2026c%2E+Towards+reliable+multimodal+disaster+severity+assessment+through+preference+optimization+and+explainable+)
65. Kaizhi Zheng, Kaiwen Zhou, Jing Gu, Yue Fan, Jialu Wang, Zonglin Di, Xuehai He, and Xin Eric Wang. 2022. Jarvis: A neuro-symbolic commonsense reasoning framework for conversational embodied agents. arXiv preprint arXiv:2208.13266. — [arXiv:2208.13266](https://arxiv.org/abs/2208.13266) [find](https://scholar.google.com/scholar?q=Kaizhi+Zheng%2C+Kaiwen+Zhou%2C+Jing+Gu%2C+Yue+Fan%2C+Jialu+Wang%2C+Zonglin+Di%2C+Xuehai+He%2C+and+Xin+Eric+Wang%2E+2022%2E+Jarvis%3A+A+neuro%2Dsymbolic+commonsense+reasoning+framework+for+conversational+embodied+agents%2E+ar)
66. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. [Minigpt-4: Enhancing vision-language understanding with advanced large language models](https://md.research.elamur.ai/free/en/papers/zhu-2023-minigpt-4-enhancing-vision-language/). arXiv preprint arXiv:2304.10592.

*Updated 1 November 2026*