The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
arXiv:2606.11470v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge. Although modern LLMs show progress in structured inference, multi-step problem solving, and contextual understanding, their reasoning behavior is often inconsistent and sensitive to prompting strategies, task design, and model scale. This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology to e
The proliferation of LLMs and their growing application across various industries necessitates a comprehensive understanding of their reasoning capabilities and limitations.
A structured analysis of LLM reasoning paradigms, methods, and failure modes is crucial for developing more reliable and sophisticated AI applications, impacting product development and strategic investment in AI.
This survey provides a foundational framework to better evaluate and improve LLM performance, potentially accelerating the development of more robust AI and informing future research directions.
- · AI researchers
- · LLM developers
- · AI-reliant businesses
- · Companies relying on unreliable 'black box' LLMs
- · Developers ignoring reasoning limitations
Improved understanding and debugging of LLM reasoning will lead to more effective model development.
The ability to quantify and mitigate reasoning failures will accelerate the deployment of LLMs in critical applications.
More reliable LLM reasoning could significantly advance the capabilities of multi-agent systems and autonomous AI agents.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL