Real-Time Reasoning Agents in Evolving Environments

ICLR 2026 Conference Submission17166 Authors

Keywords: Real-time reasoning, Language model agents, Parallel reasoning architecture

Abstract: 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*. (2) **Planning agents**, which allow *extended reasoning computation for complex problems*. Our experiments show that even state-of-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 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.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 17166