Real-Time Reasoning Agents in Evolving Environments

TL;DR

This paper introduces the concept of real-time reasoning for agents in dynamic environments, proposing new paradigms and a framework to improve timely decision-making under evolving conditions.

Contribution

It defines real-time reasoning as a new problem, develops the Real-Time Reasoning Gym, and proposes AgileThinker, a hybrid approach combining reactive and planning paradigms.

Findings

AgileThinker outperforms single-paradigm agents under time pressure.

State-of-the-art models struggle with logical and timely judgments.

The framework establishes real-time reasoning as a key testbed for practical AI agents.

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, and (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 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.