arXiv:2504. 03991v2 Announce Type: replace-cross Abstract: Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making.
arXiv:2607. 11250v1 Announce Type: cross Abstract: Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively when interacting with one another.
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.
UnifiedPlayers is a cooperative framework that jointly adapts planning, execution, and evaluation for tool-integrated reinforcement learning agents. It consists of a Planning Player that generates tasks, an Execution Player that creates multi-turn trajectories with Python tool calls, and an Evaluation Player that builds executable verifiers, all coordinated by role‑specific rewards under GRPO. The approach outperforms prior baselines on mathematical and general reasoning benchmarks and yields a verifier with high adversarial detection accuracy and more discriminative reward signals.
The paper investigates zero‑shot task generalisation in offline multi‑agent reinforcement learning by extending sequence‑modeling architectures to support multi‑task observation and action spaces and variable agent counts. It finds that increasing task diversity, rather than merely enlarging the dataset, is the key driver for robust zero‑shot transfer. Experiments on four challenging environments show a 3.2× mean improvement on held‑out tasks compared to single‑task models and outperform strong behaviour‑cloning baselines.
arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.
The paper presents UBCL, a reinforcement learning framework that generates controllable and diverse player behaviors without using human gameplay data. By defining behavior in an N‑dimensional continuous space and training a single PPO‑based multi‑agent policy with target behavior vectors, the method learns how actions affect behavioral statistics such as aggressiveness, mobility, and cooperativeness. Experiments in a custom Unity multiplayer game demonstrate that UBCL achieves greater behavioral diversity than a win‑only baseline and accurately matches specified behavior vectors across a range of targets.
The paper argues that zero‑shot generalization in robotics is limited by a lack of diverse training data, unlike digital AI where crowd‑sourced data drives progress. It defines zero‑shot generalization as coverage of the deployment distribution and shows that adding more samples from the same source only marginally reduces the unseen region, whereas new contributors significantly expand it. The authors propose a shared latent space for robot actions, combining multi‑modal alignment, generative augmentation, and noisy‑label learning, and suggest building a community of developers around a single standard robot, Origami, to generate diverse data for testing zero‑shot success.
arXiv:2601. 21754v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.
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.
The paper introduces a behavior‑aware framework to build diverse crowds of large language models (LLMs) for future prediction. By analyzing reasoning traces on independent tasks, clustering models by behavioral similarity, and selecting representative medoids, the authors demonstrate that a small, well‑chosen crowd can outperform a larger, conventional voting ensemble. Experiments with 25 LLMs across multiple benchmarks show significant reductions in model calls and inference cost while improving prediction accuracy.
General-purpose robots must handle tasks, objects and environments they were never trained on, yet zero-shot generalization remains one of the least solved problems in physical AI. In digital AI, zero...