🧑‍🔬 Saravan Rajmohan

🏛️ Affiliations

🏢MicrosoftRedmond · United States2022–2026 · 123 paperscurrent🎓Georgia Institute of TechnologyAtlanta · United States2024–2026 · 3 paperscurrent🎓Peking UniversityBeijing · China2024–2026 · 3 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2025–2026 · 2 paperscurrent🏢Microsoft ResearchCambridge · United Kingdom2024–2026 · 2 paperscurrent🎓Zhejiang UniversityHangzhou · China2026 · 2 paperscurrent🎓University of Illinois Urbana-ChampaignUrbana · United States2023–2025 · 2 papers🎓University of WashingtonSeattle · United States2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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. UFO: A UI-Focused Agent for Windows OS Interaction (2025 · 38 citations)
   Windows is a hard environment for vision-language agents. Its interfaces are dense, its screens are large, and everyday requests often require moving between several programs. The Microsoft authors present UFO, an agent that turns natural-language instructions into executed GUI actions on Windows. It relies on two…
2. LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals (2026 · 2 citations)
   The paper asks whether chain-of-thought reasoning in an LLM follows an organized path through hidden-state space, and whether that path can be used to diagnose and steer reasoning.
3. RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026 · 1 citation)
   Most code-generation benchmarks test single functions or classes, or ask models to edit existing codebases.
4. EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video (2026)
   Wearable cameras such as AR glasses could let people search their own past experiences with natural-language questions.
5. Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs (2026)
   Common test-time scaling strategies, such as majority voting and Best-of-N, can only pick from the candidates a model produces.
6. SynthAgent: Adapting Web Agents with Synthetic Supervision (2026)
   Web agents often fail on websites they never saw during training. Such sites rarely come with tasks or demonstrations, and hiring people to write them for each new site is costly. Earlier synthetic-data pipelines fix only one half of the task–trajectory pair. Some produce hallucinated, infeasible goals. Others…

All works

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

1. UFO: A UI-Focused Agent for Windows OS InteractionConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Chaoyun Zhang, Liqun Li, Shilin He, et al.2025 · 38 citations
2. Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetXing Zhang et al.2025 · 4 citations
3. LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness SignalsAnnual Meeting of the Association for Computational Linguistics (ACL)Lihao Sun, Hang Dong, Bo Qiao, et al.2026 · 2 citations
4. RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to RepositoryAnnual Meeting of the Association for Computational Linguistics (ACL)Zhiyuan Peng, Xin Yin, Pu Zhao, et al.2026 · 1 citation
5. EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric VideoFindings of the Association for Computational LinguisticsYuanmin Tang, Jue Zhang, Xiaoting Qin, et al.2026
6. Learning to Refine: Self-Refinement of Parallel Reasoning in LLMsFindings of the Association for Computational LinguisticsQibin Wang, Pu Zhao, Shaohan Huang, et al.2026
7. SynthAgent: Adapting Web Agents with Synthetic SupervisionAnnual Meeting of the Association for Computational Linguistics (ACL)Zhaoyang Wang, Yiming Liang, Xuchao Zhang, et al.2026
8. Gradient-Guided Multi-Judge Prompt Optimization ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetChenZhuo Zhao et al.2026

🤝 Co-authors here

12 of 24 co-authors with a page, the most papers together first.

• Dongmei Zhang ×5
• Qingwei Lin ×5
• Bo Qiao ×2
• Fangkai Yang ×2
• Lu Wang ×2
• Pu Zhao ×2
• Baolin Peng
• Furu Wei
• Hang Dong
• Huaxiu Yao
• Jianfeng Gao
• Jue Zhang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×4: ACL 2026 ×3
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2025
• Findings of the Association for Computational Linguistics: EMNLP 2025

🔗 Cited by

Papers of our library cite their works 34 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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