Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation Paper • 2410.13232 • Published Oct 17 • 40
Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code Paper • 2409.19715 • Published Sep 29 • 8
THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation Paper • 2406.10996 • Published Jun 16 • 32
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models Paper • 2404.02575 • Published Apr 3 • 47
