🧑‍🔬 Yitao Liang

🏛️ Affiliations

🎓Peking UniversityBeijing · China2022–2026 · 23 papersEmploymentcurrent🏛️Beijing Institute for General Artificial IntelligenceBeijing · China2022–2026 · 7 paperscurrent🎓Shanghai Business SchoolShanghai · China2026 · 1 papercurrent🎓Henan University of TechnologyZhengzhou · China2007–2025 · 47 papers🎓University of California, Los AngelesLos Angeles · United States2017–2021 · 11 papers🎓Franklin & Marshall CollegeLancaster · United States2015–2017 · 5 papers🎓East China Normal UniversityShanghai · China2017–2021 · 2 papers

🏛️UCLALos Angeles · United States2016–2021Education 2016–2021 · Ph.D., Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents (2023 · 174 citations)
   The paper tackles task planning for embodied agents in open-world settings such as Minecraft. Two problems make LLM planners fail there. Tasks need long chains of dependent sub-goals, so a plan written in one pass is often wrong. Plans also ignore which of several alternative sub-goals the agent can reach most easily…
2. Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners (2023 · 52 citations)
   This work asks where the apparent few-shot reasoning skill of LLMs actually comes from. The authors argue that it depends largely on token meanings absorbed during pretraining, which let models link concepts into shallow shortcut chains instead of applying rules formally. To test this, they remove or invert semantics…
3. RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation (2024 · 46 citations)
   Large language models that reason step by step often produce intermediate thoughts containing invented facts.

All works

6 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task AgentsarXiv:2302.01560Zihao Wang, Shaofei Cai, Guanzhou Chen, et al.2023 · 174 citations
2. Large Language Models are In-Context Semantic Reasoners rather than Symbolic ReasonersarXiv:2305.14825Xiaojuan Tang, Zilong Zheng, Jiaqi Li, et al.2023 · 52 citations
3. JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models ↗arXiv:2311.05997 · no summary yetZihao Wang et al.2023 · 47 citations
4. RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon GenerationarXiv:2403.05313Zihao Wang, Anji Liu, Haowei Lin, et al.2024 · 46 citations
5. Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction ↗arXiv:2301.10034 · no summary yetShaofei Cai et al.2023 · 18 citations
6. Proposing and solving olympiad geometry with guided tree search ↗arXiv:2412.10673 · no summary yetChi Zhang et al.2024 · 8 citations

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Anji Liu ×2
• Jiaqi Li ×2
• Xiaojian Ma ×2
• Zihao Wang ×2
• Fanxu Meng
• Muhan Zhang
• Song-Chun Zhu
• Zilong Zheng

🔗 Cited by

Papers of our library cite their works 258 times (of the 149,439 papers whose bibliographies we read); 60 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/yitao-liang/