We’re releasing a Neural MMO, a massively multiagent game environment for reinforcement learning agents. Our platform supports a large, variable number of agents within a persistent and open-ended task.
arXiv:2606. 04750v1 Announce Type: new Abstract: Instilling virtuous behavior in artificial intelligence has seen increasing interest.
arXiv:2404. 02039v5 Announce Type: replace Abstract: Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity.
We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through training in our new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported.
arXiv:2606. 04484v2 Announce Type: replace Abstract: Training reinforcement learning (RL) policies for large language model (LLM) agents requires optimizing multi-turn trajectories that interact with external environments.
Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties: first, there is a natural curriculum—the difficulty of the environment is determined by the skill of your competitors (and if you’re competing against clones of yourself, the environment exactly matches your skill level).
arXiv:2506. 14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied.
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.
arXiv:2507.11482v5 Announce Type: replace Abstract: Artificial learning systems are graduating from passive learners to increasingly autonomous agents, lending pragmatic urgency to the question of wh...
PhantomEnvironments is a framework that trains large language model agents in synthetic, rule‑generated fictional worlds. By creating multi‑turn reinforcement learning environments where agents search templated articles to answer multi‑hop questions, the approach eliminates the need for costly human data or hallucinated LLM‑generated settings. Agents trained in these zero‑cost, purely rule‑based worlds transfer effectively to real‑world multi‑hop search benchmarks, often surpassing models trained on real data, and demonstrate scalable search behavior that grows linearly with question difficulty.
arXiv:2606. 04484v1 Announce Type: new Abstract: We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning.
SwarmWorld demonstrates that homogeneous language‑model agents can self‑organize into evolving technological societies without assigned roles or direct communication. In a spatial environment, agents explore, process resources, construct artifacts, and write executable controllers that are later evaluated by a deterministic simulator. The resulting societies develop broader, more resilient technological portfolios than isolated search, with agents differentiating into exploration, construction, maintenance, and coordination roles as the world matures.
We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning. Unlike centralized frameworks that tightly couple agent rollouts with model optimization, AgentJet adopts a decoupled multi-node architecture in which swarm server nodes host trainable models and run optimization on GPU clusters, whereas swarm client nodes execute arbitrary agents on arbitrary devices.