🧑‍🔬 Swarat Chaudhuri

🏛️ Affiliations

🎓The University of Texas at AustinAustin · United States2020–2026 · 50 papersEmployment · Computer Sciencecurrent🏢Google DeepMindLondon · United Kingdom2025–2026 · 6 paperscurrent🏢GoogleMountain View · United States2026 · 1 papercurrent🏢GoogleLondon · United Kingdom2026 · 1 papercurrent🎓Rice UniversityHouston · United States2011–2021 · 66 papersEmployment🎓Pennsylvania State UniversityState College · United States2008–2024 · 18 papersEmployment🎓University of PennsylvaniaPhiladelphia · United States2003–2007 · 10 papersEducation🎓California Institute of TechnologyPasadena · United States2019–2021 · 3 papers🎓University of TorontoToronto · Canada2016 · 2 papers🎓Indian Institute of Technology KharagpurKharagpur · IndiaEducation

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 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. PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition (2024 · 93 citations)
   Neural theorem-provers are usually tested on competition benchmarks such as MiniF2F and FIMO. These sets rely mostly on high-school mathematics, and some MiniF2F items can be solved directly by SMT solvers. They also cover only some proof assistants, and they risk overlap with LLM pretraining data. PutnamBench is a…
2. MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning (2023 · 74 citations)
   Existing reasoning benchmarks for LLMs tend to fall into two camps. Some use artificial text that rule-based solvers can crack. Others involve commonsense but only one or two inference steps. MuSR (Multistep Soft Reasoning) targets the gap between them: long natural-language narratives whose solution requires both…

All works

8 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical CompetitionConference on Neural Information Processing Systems (NeurIPS)George Tsoukalas, Jasper Lee, John Jennings, et al.2024 · 93 citations
2. MuSR: Testing the Limits of Chain-of-thought with Multistep Soft ReasoningInternational Conference on Learning Representations (ICLR)Zayne Sprague, Xi Ye, Kaj Bostrom, et al.2023 · 74 citations
3. Formal Mathematical Reasoning: A New Frontier in AI ↗arXiv:2412.16075 · no summary yetKaiyu Yang et al.2024 · 49 citations
4. An In-Context Learning Agent for Formal Theorem-Proving ↗arXiv:2310.04353 · no summary yetAmitayush Thakur et al.2023 · 47 citations
5. Symbolic Regression with a Learned Concept Library ↗arXiv:2409.09359 · no summary yetArya Grayeli et al.2024 · 23 citations
6. Neural Attribute Machines for Program Generation ↗arXiv:1705.09231 · no summary yetMatthew Amodio, Swarat Chaudhuri, Thomas W. Reps2017 · 23 citations
7. Neurosymbolic Programming for Science ↗arXiv:2210.05050 · no summary yetJennifer J. Sun et al.2022 · 6 citations
8. Formal Reasoning Meets LLMs: Toward AI for Mathematics and Verification ↗Communications of the ACM · no summary yetKaiyu Yang et al.2026 · 1 citation

🤝 Co-authors here

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

• Greg Durrett
• Kaj Bostrom
• Xi Ye
• Zayne Sprague

Venues

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

• International Conference on Learning Representations (ICLR): ICLR 2023
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2024
• Communications of the ACM

🔗 Cited by

Papers of our library cite their works 449 times (of the 149,439 papers whose bibliographies we read); 69 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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