6 papers
Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning
Allen Nie, Anirudhan Badrinath, Nicholas Tomlin +5
Learning and skill mastery require extensive and deliberate practice. In many learning settings, producing high-quality pedagogical materials can require a high level of domain exp…
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
Simon Yu, Nicholas Tomlin, Marwa Abdulhai +7
Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically f…
Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents
Wenxuan Ding, Nicholas Tomlin, Greg Durrett
LLM agents are deployed in environments where they must interact to acquire information. In these scenarios, the agent must reason about inherent cost-uncertainty tradeoffs in how…
Measuring General Intelligence with Generated Games
Vivek Verma, David Huang, William Chen +2
We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data gen…
Efficacy of Language Model Self-Play in Non-Zero-Sum Games
Austen Liao, Nicholas Tomlin, Dan Klein
Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However,…
Autonomous Evaluation and Refinement of Digital Agents
Jiayi Pan, Yichi Zhang, Nicholas Tomlin +3
We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control. We experiment with multiple evaluation m…