117 citations · 269 across the 39 of their papers we have counts for
47 papers
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Shubham Agarwal, Akshat Gupta, Mike Heddes +21
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fun…
Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses
Weichen Yu, Lesly Miculicich, Bhavana Dalvi Mishra +5
Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches, however…
Harness^2: Recursive Agent Harnessing for an Open World
Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu +6
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatic…
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra +5
LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime guardrail…
AIM: Agentic Idea Management for Automated Research
Hyeong Kyu Choi, Bhavana Dalvi Mishra, Jiefeng Chen +7
Frontier LLMs are increasingly used to automate scientific research through iterative search. We distinguish idea-driven search from solution-driven search and identify three core…
EnvHarness: Awakening Static Worlds for Agent Learning
Chengsong Huang, Zifeng Wang, Rujun Han +14
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While r…
T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration
Tao Feng, Linxin Song, Jiefeng Chen +9
Migrating a machine-learning codebase across frameworks--for example from PyTorch to JAX--is a routine but costly engineering task that is fundamentally cross-paradigm: eager, stat…
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
Rui Meng, Bhavana Dalvi Mishra, Jiefeng Chen +10
Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evalua…
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra +6
As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete de…
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9
Deep research agents plan, search, evaluate evidence, and synthesize long-form reports. Training these agents with reinforcement learning (RL) is challenging because they operate o…
SkillOS: Learning Skill Curation for Self-Evolving Agents
Siru Ouyang, Jun Yan, Yanfei Chen +13
LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills disti…
LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape
Hita Kambhamettu, Bhavana Dalvi Mishra, Andrew Head +4
Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively reviewing literatu…
MARS: Modular Agent with Reflective Search for Automated AI Research
Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam +3
A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computati…
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
Jonathan Bragg, Mike D'Arcy, Nishant Balepur +36
AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions o…
HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation
Rosni Vasu, Peter Jansen, Pao Siangliulue +4
While there has been a surge of interest in automated scientific discovery (ASD), especially with the emergence of LLMs, it remains challenging for tools to generate hypotheses tha…
AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
Dhruv Agarwal, Bodhisattwa Prasad Majumder, Reece Adamson +8
The promise of autonomous scientific discovery (ASD) hinges not only on answering questions, but also on knowing which questions to ask. Most recent works in ASD explore the use of…
HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra +3
Large Language models have demonstrated promising performance in research ideation across scientific domains. Hypothesis development, the process of generating a highly specific de…
CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation
Peter Jansen, Oyvind Tafjord, Marissa Radensky +6
Despite the surge of interest in autonomous scientific discovery (ASD) of software artifacts (e.g., improved ML algorithms), current ASD systems face two key limitations: (1) they…
Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision
Zhouhang Xie, Tushar Khot, Bhavana Dalvi Mishra +4
Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purp…
From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answering
Nathaniel Weir, Bhavana Dalvi Mishra, Orion Weller +6
Recent reasoning methods (e.g., chain-of-thought, entailment reasoning) help users understand how language models (LMs) answer a single question, but they do little to reveal the L…
IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
Kevin Pu, K. J. Kevin Feng, Tovi Grossman +6
Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer…
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal +7
Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely fro…
DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
Peter Jansen, Marc-Alexandre Côté, Tushar Khot +5
Automated scientific discovery promises to accelerate progress across scientific domains. However, developing and evaluating an AI agent's capacity for end-to-end scientific reason…
Naive Bayes-based Context Extension for Large Language Models
Jianlin Su, Murtadha Ahmed, Wenbo +3
Large Language Models (LLMs) have shown promising in-context learning abilities. However, conventional In-Context Learning (ICL) approaches are often impeded by length limitations…