按年被提到
20262026 · 3 次2026
强化学习与智能体›大模型智能体·arXiv:2601.12538 · cs.AI

A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents

Tianxin Wei, Ting-Wei Li, Zhining Liu, Xuying Ning, Ze Yang, Jiaru Zou, Zhichen Zeng, Ruizhong Qiu, Xiao Lin, Dongqi Fu, Zihao Li, Mengting Ai 等 29 人 · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-01-23 · 最近 2026-08-15
2不同的人
2活跃月份
3讨论串
22被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论jasendo · 2026-01

“Solid survey. The breakdown of in-context vs post-training reasoning is a helpful lens. Curious to see how the "long-horizon interaction" challenges they flag get addressed in practice.”

Agentic Reasoning for Large Language Models原评论 ↗
被提交为 story · 3 次