Real-Time Reasoning Agents in Evolving Environments

• URL: http://arxiv.org/abs/2511.04898v1
• Date: Fri, 07 Nov 2025 00:51:02 GMT
• Title: Real-Time Reasoning Agents in Evolving Environments
• Authors: Yule Wen, Yixin Ye, Yanzhe Zhang, Diyi Yang, Hao Zhu,
• Abstract summary: We introduce real-time reasoning as a new problem formulation for agents in evolving environments.<n>Our work establishes real-time reasoning as a critical testbed for developing practical agents.
• Score: 52.21796134114843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Agentic Reasoning for Large Language Models [122.81018455095999]
  Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making.<n>Large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, but struggle in open-ended and dynamic environments.<n>Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction.
  arXiv  Detail & Related papers  (2026-01-18T18:58:23Z)
• Current Agents Fail to Leverage World Model as Tool for Foresight [61.82522354207919]
  Generative world models offer a promising remedy: agents could use them to foresee outcomes before acting.<n>This paper empirically examines whether current agents can leverage such world models as tools to enhance their cognition.
  arXiv  Detail & Related papers  (2026-01-07T13:15:23Z)
• Time-Scaling Is What Agents Need Now [14.04852184032241]
  Humans solve problems under limited cognitive resources through temporalized sequential reasoning.<n>Recent models like DeepSeek-R1 enhanced performance through explicit reasoning trajectories.<n>Time-Scaling refers to architectural design utilizing extended temporal pathways.
  arXiv  Detail & Related papers  (2026-01-06T05:01:17Z)
• Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation [42.38513187601995]
  Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks.<n>Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent proposes plans and monitors progress while a reasoning agent executes subtasks through sequential conversational turns.<n>Despite promising performance, we identify a critical limitation: lazy agent behavior, in which one agent dominates while the other contributes little, undermining collaboration and collapsing the setup to an ineffective single agent.<n>We propose a verifiable reward mechanism that encourages deliberation by allowing the reasoning agent to discard noisy outputs, consolidate instructions, and restart its reasoning process
  arXiv  Detail & Related papers  (2025-11-04T06:37:31Z)
• GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments [56.007498767771075]
  GSM-Agent is a novel benchmark for evaluating agentic reasoning in complex environments.<n>We analyze the agentic reasoning patterns by cluster the environment's document embeddings into nodes, and map each tool call to its nearest node.<n>We propose a tool-augmented test-time scaling method to improve LLM's agentic reasoning performance by adding tools to encourage models to revisit.
  arXiv  Detail & Related papers  (2025-09-26T07:24:37Z)
• DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking [12.71072798544731]
  DUMA embodies a dual-mind mechanism through the utilization of two generative Large Language Models (LLMs) dedicated to fast and slow thinking respectively. We have constructed a conversational agent to handle online inquiries in the real estate industry.
  arXiv  Detail & Related papers  (2023-10-27T11:43:46Z)
• From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning [66.98861219674039]
  Heuristic-Analytic Reasoning (HAR) strategies drastically improve the coherence of rationalizations for model decisions. Our findings suggest that human-like reasoning strategies can effectively improve the coherence and reliability of PLM reasoning.
  arXiv  Detail & Related papers  (2023-10-24T19:46:04Z)
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning [68.74447489372037]
  We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning. A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
  arXiv  Detail & Related papers  (2021-06-25T00:21:41Z)
• Modelling Multi-Agent Epistemic Planning in ASP [66.76082318001976]
  This paper presents an implementation of a multi-shot Answer Set Programming-based planner that can reason in multi-agent epistemic settings. The paper shows how the planner, exploiting an ad-hoc epistemic state representation and the efficiency of ASP solvers, has competitive performance results on benchmarks collected from the literature.
  arXiv  Detail & Related papers  (2020-08-07T06:35:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.