teammate
Perplexity's 'teammates' are the company's AI agents for daily work tasks
Perplexity has launched its personal AI agents called teammates, which are designed to be able to tackle ongoing work autonomously with minimal supervision. The agents work inside Perplexity Computer, the company's cloud-based agentic assistant that can perform multi-step tasks for you. Perplexity explains that the new agents build on top of Computer and come with additional capabilities for ongoing, large-scale work. You'll be able to assign each teammate its own role or task that they can all then perform simultaneously. Teammates work together, and they can even manage other teammates to make sure your tasks are getting done.
Google Gemini 4 agents just beat Minecraft with no human intervention
Google's Deepmind "AlphaGo" AI is famous for winning at Go, but the company's latest Gemini AI just mastered a far more complex game. Four Gemini 4 Argon agents beat Minecraft's final "Ender Dragon" foe with no human intervention by working individually while sharing tips, threats and mistakes, Google researchers revealed in a new paper. The experiment shows how general agentic AI models can now beat complex games, a feat that used to required custom AI software. To tackle Minecraft, the Gemini 4 team set four AI agents into a sandboxed, randomized Minecraft survival world with a goal to defeat the Ender Dragon. No roles, strategies or game-specific tools were assigned.
Efficient Multi-agent Communication via Self-supervised Information Aggregation
Utilizing messages from teammates can improve coordination in cooperative Multi-agent Reinforcement Learning (MARL). To obtain meaningful information for decision-making, previous works typically combine raw messages generated by teammates with local information as inputs for policy. However, neglecting the aggregation of multiple messages poses great inefficiency for policy learning. Motivated by recent advances in representation learning, we argue that efficient message aggregation is essential for good coordination in MARL. In this paper, we propose Multi-Agent communication via Self-supervised Information Aggregation (MASIA), with which agents can aggregate the received messages into compact representations with high relevance to augment the local policy. Specifically, we design a permutation invariant message encoder to generate common information aggregated representation from raw messages and optimize it via reconstructing and shooting future information in a self-supervised manner. Each agent would utilize the most relevant parts of the aggregated representation for decision-making by a novel message extraction mechanism. Empirical results demonstrate that our method significantly outperforms strong baselines on multiple cooperative MARL tasks for various task settings.
Agentic AI as Undercover Teammates: Argumentative Knowledge Construction in Hybrid Human-AI Collaborative Learning
Yan, Lixiang, Jin, Yueqiao, Zhao, Linxuan, Martinez-Maldonado, Roberto, Li, Xinyu, Guan, Xiu, Guo, Wenxin, Han, Xibin, Gaลกeviฤ, Dragan
Generative artificial intelligence (AI) agents are increasingly embedded in collaborative learning environments, yet their impact on the processes of argumentative knowledge construction remains insufficiently understood. Emerging conceptualisations of agentic AI and artificial agency suggest that such systems possess bounded autonomy, interactivity, and adaptability, allowing them to engage as epistemic participants rather than mere instructional tools. Building on this theoretical foundation, the present study investigates how agentic AI, designed as undercover teammates with either supportive or contrarian personas, shapes the epistemic and social dynamics of collaborative reasoning. Drawing on Weinberger and Fischer's (2006) four-dimensional framework, participation, epistemic reasoning, argument structure, and social modes of co-construction, we analysed synchronous discourse data from 212 human and 64 AI participants (92 triads) engaged in an analytical problem-solving task. Mixed-effects and epistemic network analyses revealed that AI teammates maintained balanced participation but substantially reorganised epistemic and social processes: supportive personas promoted conceptual integration and consensus-oriented reasoning, whereas contrarian personas provoked critical elaboration and conflict-driven negotiation. Epistemic adequacy, rather than participation volume, predicted individual learning gains, indicating that agentic AI's educational value lies in enhancing the quality and coordination of reasoning rather than amplifying discourse quantity. These findings extend CSCL theory by conceptualising agentic AI as epistemic and social participants, bounded yet adaptive collaborators that redistribute cognitive and argumentative labour in hybrid human-AI learning environments.
IPPO Learns the Game, Not the Team: A Study on Generalization in Heterogeneous Agent Teams
Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates, often using parameter sharing and a single policy architecture. This opens the question: to what extent do self-play PPO agents learn general coordination strategies grounded in the underlying game, compared to overfitting to their training partners' behaviors? This paper investigates the question using the Heterogeneous Multi-Agent Challenge (HeMAC) environment, which features distinct Observer and Drone agents with complementary capabilities. We introduce Rotating Policy Training (RPT), an approach that rotates heterogeneous teammate policies of different learning algorithms during training, to expose the agent to a broader range of partner strategies. When playing alongside a withheld teammate policy (DDQN), we find that RPT achieves similar performance to a standard self-play baseline, IPPO, where all agents were trained sharing a single PPO policy. This result indicates that in this heterogeneous multi-agent setting, the IPPO baseline generalizes to novel teammate algorithms despite not experiencing teammate diversity during training. This shows that a simple IPPO baseline may possess the level of generalization to novel teammates that a diverse training regimen was designed to achieve.