---
title: "Karthik Narasimhan — all works — Elamur Research"
description: "All 43 works of Karthik Narasimhan in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/karthik-narasimhan/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/karthik-narasimhan/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Karthik Narasimhan](https://md.research.elamur.ai/free/en/authors/karthik-narasimhan/) / all works

# Karthik Narasimhan — all works

43 works · [← Karthik Narasimhan](https://md.research.elamur.ai/free/en/authors/karthik-narasimhan/)

1. **[Tree of Thoughts: Deliberate Problem Solving with Large Language Models ↗](https://arxiv.org/abs/2305.10601) arXiv:2305.10601 · no summary yet**Shunyu Yao et al.*2023 · 2,671 citations*
2. [**ReAct: Synergizing Reasoning and Acting in Language Models arXiv:2210.03629**Shunyu Yao, Jeffrey Zhao, Dian Yu, et al.*2022 · 2,591 citations*](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/)
3. **[Reflexion: Language Agents with Verbal Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Noah Shinn, Federico Cassano, Edward Berman, et al.*2023 · 2,271 citations*
4. [**SWE-bench: Can Language Models Resolve Real-World GitHub Issues? arXiv:2310.06770**Carlos E. Jimenez, John Yang, Alexander Wettig, et al.*2024 · 704 citations*](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/)
5. **[SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**John Yang, Carlos E. Jimenez, Alexander Wettig, et al.*2024 · 552 citations*
6. **[WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://md.research.elamur.ai/free/en/papers/yao-2022-webshop-towards-scalable-real-world/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Shunyu Yao, Howard Chen, John Yang, et al.*2022 · 420 citations*
7. **[Language Understanding for Text-based Games Using Deep Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/narasimhan-2015-language-understanding-text-based-games/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Karthik Narasimhan, Tejas Kulkarni, Regina Barzilay*2015 · 380 citations*
8. **[Toxicity in chatgpt: Analyzing persona-assigned language models](https://md.research.elamur.ai/free/en/papers/deshpande-2023-toxicity-chatgpt-analyzing-persona-assigned/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, et al.*2023 · 353 citations*
9. **[Cognitive Architectures for Language Agents ↗](https://arxiv.org/abs/2309.02427) arXiv:2309.02427 · no summary yet**Theodore R. Sumers et al.*2023 · 189 citations*
10. **[Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning ↗](https://aclanthology.org/D16-1261/) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · no summary yet**Karthik Narasimhan, Adam Yala, Regina Barzilay*2016 · 183 citations*
11. [**τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains arXiv:2406.12045**Shunyu Yao, Noah Shinn, Pedram Razavi, et al.*2024 · 137 citations*](https://md.research.elamur.ai/free/en/papers/yao-2024-tau-bench-benchmark-tool/)
12. **[Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://md.research.elamur.ai/free/en/papers/yao-2020-keep-calm-explore-language-models/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Shunyu Yao, Rohan Rao, Matthew Hausknecht, et al.*2020 · 130 citations*
13. **[sk_p: a neural program corrector for MOOCs ↗](https://doi.org/10.1145/2984043.2989222) ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH) · no summary yet**Yewen Pu et al.*2016 · 121 citations*
14. [**FireAct: Toward Language Agent Fine-tuning arXiv:2310.05915**Baian Chen, Chang Shu, Ehsan Shareghi, et al.*2023 · 101 citations*](https://md.research.elamur.ai/free/en/papers/chen-2023-fireact-toward-language-agent-fine/)
15. **[Nonparametric Spherical Topic Modeling with Word Embeddings ↗](https://aclanthology.org/P16-2087/) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yet**Kayhan Batmanghelich et al.*2016 · 98 citations*
16. **[Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge ↗](https://aclanthology.org/D16-1197/) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · no summary yet**Nicholas Locascio et al.*2016 · 97 citations*
17. **[InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://md.research.elamur.ai/free/en/papers/yang-2023-intercode-standardizing-benchmarking-interactive-coding/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**John Yang, Akshara Prabhakar, Karthik Narasimhan, et al.*2023 · 95 citations*
18. **[Machine Comprehension with Discourse Relations](https://md.research.elamur.ai/free/en/papers/narasimhan-2015-machine-comprehension-discourse-relations/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Karthik Narasimhan, Regina Barzilay*2015 · 92 citations*
19. **[An Unsupervised Method for Uncovering Morphological Chains ↗](https://aclanthology.org/Q15-1012/) Transactions of the Association for Computational Linguistics · no summary yet**Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola*2015 · 88 citations*
20. [**τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment arXiv:2506.07982**Victor Barres, Honghua Dong, Soham Ray, et al.*2025 · 76 citations*](https://md.research.elamur.ai/free/en/papers/barres-2025-tau-2-bench-evaluating-conversational/)
21. **[Representation Learning for Grounded Spatial Reasoning](https://md.research.elamur.ai/free/en/papers/janner-2018-representation-learning-grounded-spatial-reasoning/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Michael Janner, Karthik Narasimhan, Regina Barzilay*2018 · 70 citations*
22. **[Anthropomorphization of AI: Opportunities and Risks ↗](https://aclanthology.org/2023.nllp-1.1/) Proceedings of the Natural Legal Language Processing Workshop 2023 · no summary yet**Ameet Deshpande et al.*2023 · 67 citations*
23. **[Can Rationalization Improve Robustness? ↗](https://aclanthology.org/2022.naacl-main.278/) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Howard Chen et al.*2022 · 59 citations*
24. **[Morphological Segmentation for Keyword Spotting ↗](https://aclanthology.org/D14-1095/) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yet**Karthik Narasimhan et al.*2014 · 52 citations*
25. **[SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? ↗](https://arxiv.org/abs/2410.03859) arXiv (Cornell University) · no summary yet**John Jeongseok Yang et al.*2024 · 48 citations*
26. **[Self-Attention Networks Can Process Bounded Hierarchical Languages ↗](https://arxiv.org/abs/2105.11115) arXiv:2105.11115 · no summary yet**Shunyu Yao et al.*2021 · 43 citations*
27. [**Can Language Models Solve Olympiad Programming? arXiv:2404.10952**Quan Shi, Michael Tang, Karthik Narasimhan, et al.*2024 · 28 citations*](https://md.research.elamur.ai/free/en/papers/shi-2024-language-models-solve-olympiad-programming/)
28. **[Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents ↗](https://aclanthology.org/2021.naacl-main.247/) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Shunyu Yao, Karthik Narasimhan, Matthew Hausknecht*2021 · 26 citations*
29. **[C-STS: Conditional Semantic Textual Similarity ↗](https://aclanthology.org/2023.emnlp-main.345/) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yet**Ameet Deshpande et al.*2023 · 25 citations*
30. [**COLLIE: Systematic Construction of Constrained Text Generation Tasks arXiv:2307.08689**Shunyu Yao, Howard Chen, Austin W. Hanjie, et al.*2023 · 23 citations*](https://md.research.elamur.ai/free/en/papers/yao-2023-collie-systematic-construction-constrained-text/)
31. **[Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting ↗](https://arxiv.org/abs/2510.18874) arXiv (Cornell University) · no summary yet**Howard Chen et al.*2025 · 21 citations*
32. **[Unsupervised Learning of Morphological Forests ↗](https://aclanthology.org/Q17-1025/) Transactions of the Association for Computational Linguistics · no summary yet**Jiaming Luo, Karthik Narasimhan, Regina Barzilay*2017 · 16 citations*
33. **[LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks ↗](https://aclanthology.org/2025.coling-industry.55/) Proceedings of the 31st International Conference on Computational Linguistics: Industry Track · no summary yet**Akshara Prabhakar et al.*2025 · 14 citations*
34. **[Contextual Experience Replay for Self-Improvement of Language Agents ↗](https://aclanthology.org/2025.acl-long.694/) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Yitao Liu et al.*2025 · 13 citations*
35. **[Controllable Text Generation with Language Constraints ↗](https://arxiv.org/abs/2212.10466) arXiv (Cornell University) · no summary yet**Howard Chen et al.*2022 · 11 citations*
36. **[SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark ↗](https://openalex.org/W3214506775) neural information processing systems · no summary yet**Victor W. Zhong et al.*2021 · 9 citations*
37. **[Deep Transfer in Reinforcement Learning by Language Grounding. ↗](https://arxiv.org/abs/1708.00133) arXiv (Cornell University) · no summary yet**Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola*2017 · 9 citations*
38. **[SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark ↗](https://arxiv.org/abs/2110.10661) arXiv (Cornell University) · no summary yet**Zhong, Victor et al.*2021 · 7 citations*
39. **[Humans are Missing from AI Coding Agent Research ↗](https://arxiv.org/abs/2608.12355) arXiv (Cornell University) · no summary yet**Zora Z. Wang et al.*2026 · 6 citations*
40. **[Referral Augmentation for Zero-Shot Information Retrieval ↗](https://aclanthology.org/2024.findings-acl.798/) Findings of the Association for Computational Linguistics: ACL 2024 · no summary yet**Michael Tang et al.*2024 · 3 citations*
41. **[When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration ↗](https://doi.org/10.52202/085713-3512) neural information processing systems · no summary yet**Quan Shi et al.*2025 · 2 citations*
42. **[Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning ↗](https://arxiv.org/abs/2605.00347) arXiv (Cornell University) · no summary yet**Chengshuai Shi et al.*2026*
43. **[An Unsupervised Method for Uncovering Morphological Chains (Open Access, Publisher's Version) ↗](https://openalex.org/W2776643988) no summary yet**Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola*2015*