The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces Trajectory-guided Joint Policy Optimization (TJPO), a reinforcement‑learning framework that explicitly encourages diversity in the trajectories of large‑language‑model agents. By defining task‑specific trajectory descriptors, TJPO measures and optimizes diversity as a set‑level function, avoiding population‑based training. Experiments on Sokoban and ALFWorld demonstrate that TJPO yields diverse, interpretable behaviors while preserving strong task performance.
arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.
arXiv:2604. 17244v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents for sequential decision-making struggle to produce diverse outputs.
arXiv:2501. 04426v2 Announce Type: replace-cross Abstract: Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift without additional environment interaction.
The paper introduces RePPO, a method that adapts Proximal Policy Optimization to jointly optimize a compact population of diverse, high‑quality policies using a population‑dependent, dynamically shaped reward. RePPO achieves a strong quality‑diversity tradeoff on standard continuous‑control tasks and scales to larger policy and behavior spaces, maintaining quality while significantly increasing diversity in pixel‑based tasks. The authors also demonstrate RePPO’s applicability to fine‑tuning large language models, showing for the first time that quality‑diversity reinforcement learning can scale to this domain.
arXiv:2509.15194v4 Announce Type: replace-cross Abstract: Large language models (LLMs) can improve through reinforcement learning with verifiable rewards (RLVR), but many settings lack reference answ...