Agentic Reasoning for Large Language Models
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and dynamic environments. Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction. In this survey, we organize agentic reasoning along three complementary dimensions. First, we characterize environmental dynamics through three layers: foundational agentic reasoning, which establishes core single-agent capabilities including planning, tool use, and search in stable environments; self-evolving agentic reasoning, which studies how agents refine these capabilities through feedback, memory, and adaptation; and collective multi-agent reasoning, which extends intelligence to collaborative settings involving coordination, knowledge sharing, and shared goals. Across these layers, we distinguish in-context reasoning, which scales test-time interaction through structured orchestration, from post-training reasoning, which optimizes behaviors via reinforcement learning and supervised fine-tuning. We further review representative agentic reasoning frameworks across real-world applications and benchmarks, including science, robotics, healthcare, autonomous research, and mathematics. This survey synthesizes agentic reasoning methods into a unified roadmap bridging thought and action, and outlines open challenges and future directions, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG s…
Decision MakingRAGRetrievalRetrieval-augmented Generation+1VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and …
M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
While reasoning has become a central capability of large language models (LLMs), the reasoning patterns required for different scenarios are often misaligned. Mathematical reasoning typically relies on intrinsic logic to…
Mathematical ReasoningMulti-Task LearningAgentic Reasoning: Reasoning LLMs with Tools for the Deep Research
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Unlike conventional LLM-based reasoning approaches, which rely solely on internal …
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+3LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
Recent advances in the intrinsic reasoning capabilities of large language models (LLMs) have given rise to LLM-based agent systems that exhibit near-human performance on a variety of automated tasks. However, although th…