MOSAIC is an open‑source platform that allows agents from different decision‑making paradigms—such as reinforcement learning policies, large language models, vision‑language models, and human operators—to operate together in shared reinforcement learning environments. It achieves this through an IPC‑based worker protocol that isolates each agent’s training and inference logic, an operator abstraction that maps any agent to a minimal universal interface, and a deterministic evaluation framework offering both manual lock‑step and automated script modes for reproducible experiments.
arXiv:2606. 13578v1 Announce Type: cross Abstract: Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach.
arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component o...
arXiv:2606. 17511v1 Announce Type: cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment.
arXiv:2606. 09138v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw.
arXiv:2609. 30971v1 Announce Type: new Abstract: Embodied agents offer a promising route to automating scientific experimentation, yet their progress is constrained by the lack of reliable and systematic evaluation environments.
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.
arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.
arXiv:2602. 05965v2 Announce Type: replace-cross Abstract: Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.
arXiv:2608.22167v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL framework...
arXiv:2607. 25446v1 Announce Type: new Abstract: Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol).
arXiv:2606. 04484v1 Announce Type: new Abstract: We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning.
AeroWeaver is a new embodied‑agent harness that integrates large language model (LLM) decision making with the executable skills of individual UAVs, enabling distributed, adaptive swarm execution. It connects semantic mission decisions to governed skills, organizes role‑conditioned local agents for coordination, and refines skill selection online using role‑indexed state‑action‑reward experience. Experiments demonstrate that AeroWeaver maintains valid skill execution without a central joint‑action generator and supports reward‑guided, training‑free adaptive learning from accumulated execution experience.