Real-Time Reasoning Agents in Evolving Environments

Agents in the real world must make not only logical but also timely judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still unfolding. Despite advances in language model reasoning, existing approaches fail to account for this dynamic nature. We introduce real-time reasoning as a new problem formulation for agents in evolving environments and build Real-Time Reasoning Gym to demonstrate it. We study two paradigms for deploying language models in agents: (1) reactive agents, which employ language models with bounded reasoning computation for rapid responses, and ( 2 ) planning agents, which allow extended reasoning computation for complex problems. Our experiments show that even stateof-the-art models struggle with making logical and timely judgments in either paradigm. To address this limitation, we propose AgileThinker, which simultaneously engages both reasoning paradigms. AgileThinker consistently outperforms agents engaging only one reasoning paradigm as the task difficulty and time pressure rise, effectively balancing reasoning depth and response latency. Our work establishes real-time reasoning as a critical testbed for developing practical agents and provides a foundation for research in temporally constrained AI systems, highlighting a path toward real-time capable agents. Car Moving While Agent Thinking Apples Timing Out While Agent Thinking Partners Acting While Agent Thinking tokens/step 1.0 Figure 1 | Upper: Three real-time games, Freeway, Snake, and Overcooked. Lower: Under cognitive load and time pressure, AgileThinker, engaging both reactive and planning reasoning, consistently outperforms agents that engage either of them. Scores are averaged across different games.