Business Arena: Benchmarking LLM Agents in a Realistic Marketplace
A long-horizon marketplace for measuring how LLM agents create or lose value through sourcing, pricing, inventory, service, compliance, and capital decisions.
Publications
Research on long-horizon LLM agents, post-training, data attribution, model safety, and AI for science.
FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning
A reinforcement-learning framework with item-level counterfactual rewards and uncertainty-aware scaling for adaptable LLM recommenders.
DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
A unified benchmark and public leaderboard for evaluating LLM data-attribution methods across selection, safety, and factual attribution.
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
A targeted attribution method for identifying harmful training samples and reducing unsafe model behavior after filtering and retraining.
Bridging AI and Science: Implications from a Large-Scale Literature Analysis of AI4Science
A large-scale map of the gaps between scientific problems and the AI methods currently used to address them.
dattri: A Library for Efficient Data Attribution
An open-source library that unifies efficient data-attribution methods, utilities, and reproducible benchmarks behind a common API.
Interpreting Spatial Reasoning Capabilities in Language Models
An interpretability study of where and how spatial reasoning capabilities emerge inside language models.