Bhavana Dalvi Mishra

Staff Research Scientist
Google

Email: bhavana.dalvi2023 AT gmail DOT com


Contact Google Scholar Semantic Scholar

About Me

I am a Staff Research Scientist at Google working on Agents and AI Research. My research interests are in the area of AI Agents, Interactive reasoning and Scientific Discovery. Before joining Google, I was a Lead Research Scientist at AI2 (2015-2025). I received my Ph.D. in Computer Science from the Carnegie Mellon University in 2015, advised by Prof. William Cohen and Prof. Jamie Callan. I completed Masters in Computer Science from the Indian Institute of Technology, Bombay in 2007. Prior to PhD, I worked at Google R&D Bangalore for two years. Besides research, I love hiking, meditation, and music.

Selected Publications

The complete list of publications can be seen from my Google Scholar page.
* indicates equal contribution

Self-Evolving Agents, AI Scientists

  • MARS: Modular Agent with Reflective Search for Automated AI Research [Paper]
    Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam, Rui Meng, Tomas Pfister, Jinsung Yoon
    ICML 2026.
  • ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence [Paper] [Website]
    Rui Meng, Bhavana Dalvi Mishra*, Jiefeng Chen*, Chun-Liang Li, Palash Goyal, Mihir Parmar, Yiwen Song, Yale Song, Rajarishi Sinha, Parthasarathy Ranganathan, Burak Gokturk, Jinsung Yoon, Tomas Pfister
    arXiv 2026.
  • RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards [Paper]
    Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan, Yanfei Chen, Chun-Liang Li, Long T. Le, Rujun Han, George Lee, Hanghang Tong, Chen-Yu Lee, Tomas Pfister
    arXiv 2026.
  • LiSA: Lifelong Safety Adaptation via Conservative Policy Induction [Paper]
    Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra, Mihir Parmar, Phillip Wallis, Bharath Chandrasekhar, Kyomin Jung, Tomas Pfister, Long T. Le
    arXiv 2026.
  • SkillOS: Learning Skill Curation for Self-Evolving Agents [Paper]
    Siru Ouyang, Jun Yan, Yanfei Chen, Rujun Han, Zifeng Wang, Bhavana Dalvi Mishra, Rui Meng, Chun-Liang Li, Yizhu Jiao, Kaiwen Zha, Maohao Shen, Vishy Tirumalashetty, George Lee, Jiawei Han, Tomas Pfister, Chen-Yu Lee
    arXiv 2026.
  • Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence [Paper]
    Linxin Song, Jiefeng Chen, Yue Huang, Bhavana Dalvi Mishra, Chi Wang, Jieyu Zhao, Jinsung Yoon, Tomas Pfister
    arXiv 2026.
  • HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation [Paper]
    Rosni Vasu, Peter Jansen, Pao Siangliulue, Bhavana Dalvi Mishra, et al.
    arXiv 2025.
  • LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape [Paper]
    Hita Kambhamettu, Bhavana Dalvi Mishra, Andrew Head, Jonathan Bragg, Aakanksha Naik, Joseph Chee Chang, Pao Siangliulue
    arXiv 2026.
  • AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite [Paper]
    Jonathan Bragg, Mike D'Arcy, Nishant Balepur, Dan Bareket, Bhavana Dalvi Mishra, Sergey Feldman, Dany Haddad, Jena Hwang, Peter Jansen, Varsha Kishore, Bodhisattwa Prasad Majumder, Aakanksha Naik, Sigal Rahamimov, Kyle Richardson, Amanpreet Singh, Harshit Surana, Aryeh Tiktinsky, Rosni Vasu
    ICLR 2026 (Oral).

Generative AI agents for Discovery

  • HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance [Paper]
    Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, Cristina Sarasua, Peter Clark, Abraham Bernstein
    EMNLP 2025.
  • DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [Paper] [Website]
    Bodhisattwa Prasad Majumder*, Harshit Surana*, Dhruv Agarwal*, Bhavana Dalvi Mishra*, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, Peter Clark
    ICLR 2025.
  • CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation [Paper] [Website]
    Peter Jansen, Oyvind Tafjord, Marissa Radensky, Pao Siangliulue, Tom Hope, Bhavana Dalvi Mishra, Bodhisattwa Majumder, Daniel S. Weld, Peter Clark
    ACL 2025 (Findings).
  • IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback [Paper]
    Kevin Pu, K. J. Kevin Feng, Tovi Grossman, Tom Hope, Bhavana Dalvi Mishra*, Matt Latzke, Jonathan Bragg, Joseph Chee Chang, Pao Siangliulue
    CHI 2025.
  • Proceedings of the First Workshop on AI and Scientific Discovery: Directions and Opportunities (AISD) [Website]
    Peter Jansen, Bhavana Dalvi Mishra, Harsh Trivedi, Bodhisattwa Majumder, Tom Hope, Tushar Khot, Doug Downey, Eric Horvitz
    NAACL 2025.
  • Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision, [Paper]
    Zhouhang Xie, Tushar Khot, Bhavana Dalvi Mishra, Harshit Surana, Julian McAuley, Peter Clark, Bodhisattwa Majumder
    NAACL 2025.
  • DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents [Paper] [Website]
    Peter Jansen, Marc-Alexandre Côté, Tushar Khot, Erin Bransom, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Oyvind Tafjord, Peter Clark
    NeurIPS 2024 (Benchmark Track, Spotlight).

Continual Learning with Interaction

  • Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills [Paper] [Website]
    Kolby Nottingham, Bodhisattwa Prasad Majumder*, Bhavana Dalvi Mishra*, Sameer Singh, Peter Clark, Roy Fox
    ICML 2024.
  • CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization [Paper] [Website]
    Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Peter Jansen, Oyvind Tafjord, Niket Tandon, Li Zhang, Chris Callison-Burch, Peter Clark
    COLM 2024.

Explainable Teachable Reasoning

  • From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answering [Paper]
    Nathaniel Weir, Bhavana Dalvi Mishra, Orion Weller, Oyvind Tafjord, Sam Hornstein, Alexander Sabol, Peter Jansen, Benjamin Van Durme, Peter Clark
    ICLR 2025.
  • Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic [Paper]
    Nathaniel Weir, Kate Sanders, Orion Weller, Shreya Sharma, Dongwei Jiang, Zhengping Zhang, Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Jansen, Peter Clark, Benjamin Van Durme
    EMNLP 2024.
  • Proceedings of the 2nd Workshop on Natural Language Reasoning and Structured Explanations (NLRSE) [Website]
    Greg Durrett, Bhavana Dalvi Mishra, Peter Jansen, Danilo Ribeiro, Lionel Wong, Xi Ye, Wenting Zhao, Ben Lipkin
    ACL 2024.
  • Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE) [Website]
    Bhavana Dalvi Mishra, Greg Durrett, Peter Jansen, Danilo Neves Ribeiro, Jason Wei
    ACL 2023.
  • Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement [Paper] [Dataset] [Blog]
    Bhavana Dalvi Mishra, Oyvind Tafjord, Peter Clark
    EMNLP 2022.
  • Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning
    [Paper] [Data] [Code] [Blog]
    Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark
    EMNLP 2022.
  • Explaining Answers with Entailment Trees [Paper] [Data] [Code]
    Bhavana Dalvi Mishra*, Peter Jansen*, Oyvind Tafjord, Zhengnan Xie, Hannah Smith, Leighanna Pipatanangkura, Peter Clark
    EMNLP 2021.
  • ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language [Paper] [Data] [Demo]
    Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark
    Findings of ACL 2021.

Mental Models behind Language Models

  • Do language models have coherent mental models of everyday things? [Paper] [Website] [Blog]
    Yuling Gu, Bhavana Dalvi Mishra, Peter Clark
    ACL 2023.
  • Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE [Paper] [Blog]
    Yuling Gu, Yao Fu, Valentina Pyatkin, Ian Magnusson, Bhavana Dalvi Mishra, Peter Clark
    The Third Workshop on Figurative Language Processing at EMNLP 2022.
  • DREAM: Improving Situational QA by First Elaborating the Situation [Paper] [Website] [Blog]
    Yuling Gu, Bhavana Dalvi Mishra, Peter Clark
    NAACL 2022.

Procedural Reasoning

  • A Dataset for Tracking Entities in Open Domain Procedural Text [Paper] [Data] [Code]
    Niket Tandon, Keisuke Sakaguchi, Bhavana Dalvi Mishra, Dheeraj Rajagopal, Peter Clark, Michal Guerquin, Kyle Richardson, Eduard Hovy
    EMNLP 2020.
  • Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text [Paper]
    Bhavania Dalvi Mishra*, Niket Tandon*, Antoine Bosselut, Wen-tau Yih, Peter Clark
    EMNLP 2020.
  • WIQA: A dataset for "What if..." reasoning over procedural text [Paper] [Data] [Code]
    Niket Tandon*, Bhavana Dalvi Mishra*, Keisuke Sakaguchi, Antoine Bosselut, Peter Clark
    EMNLP 2019.
  • Reasoning about Actions and State Changes by Injecting Commonsense Knowledge [Paper] [Data] [Code]
    Niket Tandon*, Bhavana Dalvi Mishra*, Joel Grus, Wen-tau Yih, Antoine Bosselut, Peter Clark
    EMNLP 2018.