Bhavana Dalvi Mishra
I am a Staff Research Scientist at Google, specializing in self-evolving agents, interactive reasoning, and AI for scientific discovery. My current focus is on building intelligent systems that can adapt dynamically, reason effectively, and accelerate how we process complex information. I am deeply committed to fostering the next generation of AI talent and am always open to mentoring student researchers and partnering with internal teams across Google in pushing the boundaries of AI reasoning and agent self-evolution. https://scholar.google.com/citations?hl=en&user=9e0uFr4AAAAJ&view_op=list_works&authuser=1&sortby=pubdate
Prior to Google, I was a Lead Research Scientist at the Allen Institute for AI (Ai2). I hold a Ph.D. in Computer Science from Carnegie Mellon University and a Master's from IIT Bombay. My research contributions have been honored with a Google Ph.D. Fellowship, CMU's Barbara Lazarus Women@IT Fellowship, and two Best Paper runner-up awards.
Prior to Google, I was a Lead Research Scientist at the Allen Institute for AI (Ai2). I hold a Ph.D. in Computer Science from Carnegie Mellon University and a Master's from IIT Bombay. My research contributions have been honored with a Google Ph.D. Fellowship, CMU's Barbara Lazarus Women@IT Fellowship, and two Best Paper runner-up awards.
Authored Publications
Sort By
Preview abstract
Autonomous research agents can now produce competitive solutions and complete manuscripts, yet their papers routinely contain fabricated citations, method descriptions disconnected from the code, and scores on incorrect scales---failures invisible to evaluations that assess fluency rather than evidentiary grounding. The core problem is verifiability: no existing system maintains a traceable chain from each claim in the paper to its grounding evidence, and current evaluation protocols assess output fluency rather than evidentiary grounding. We address this with Chaine-of-Evidence (CoE), a verifiability standard requiring every claim to trace to its grounding evidence, and instantiate it in Scientist One, an end-to-end research system that maintains evidence chains natively, and CoE Audit, an evaluation protocol with four integrity checks targeting the most damaging chain failures. Auditing 60 papers from four systems, we find every baseline exhibits at least one failure: phantom citations at 4--25%, method-code alignment in at most 2/15 papers. Scientist One achieves zero phantom citations (0/830), the highest alignment rate (7/15), and competitive solver scores.
View details
Preview abstract
Automating AI research differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often generating monolithic scripts that ignore execution costs and causal factors. We introduce MARS (Modular Agent with Reflective Search), a framework optimized for autonomous AI research. MARS relies on three pillars: (1) Budget-Aware Planning via cost-constrained Monte Carlo Tree Search (MCTS) to explicitly balance performance with execution expense; (2) Modular Construction, employing a "Design-Decompose-Implement" pipeline to manage complex research repositories; and (3) Comparative Reflective Memory, which addresses credit assignment by analyzing solution differences to distill high-signal insights. MARS achieves state-of-the-art performance among open-source frameworks on MLE-Bench under comparable settings, maintaining competitiveness with the global leaderboard's top methods. Furthermore, the system exhibits qualitative "Aha!" moments, where 63% of all utilized lessons originate from cross-branch transfer, demonstrating that the agent effectively generalizes insights across search paths.
View details
