LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure

Daksh Mittal, Tommaso Castellani, Thomson Yen, Naimeng Ye, Fangyu Wu, Minghui Chen, Tiffany Cai, Emmanouil Koukoumidis, William Zeng, Hongseok Namkoong in arXiv preprint

June 13, 2026

Authors: Daksh Mittal, Tommaso Castellani, Thomson Yen, Naimeng Ye, Fangyu Wu, Minghui Chen, Tiffany Cai, Emmanouil Koukoumidis, William Zeng, Hongseok Namkoong

Publication: arXiv preprint, 2026

Overview

LatentGym provides task sequences governed by shared, controllable hidden variables. Its evaluation separates an agent’s ability to discover that structure from its ability to use the information in later decisions. The study examines adaptation failures, post-training on related tasks, and the effects of feedback between tasks.

Posted on:: June 13, 2026

Length:: 1 minute read, 72 words

Categories:: arXiv preprint

Tags:: LLM Agents Experiential Learning Sequential Decision-Making Personalization

See Also:: Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization; A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning; FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation