Unverified50% confidenceFactExact time
早在2022年，DeepMind的RLAM和Meta的ToolFormer论文就已论证了语言模型自主调用外部工具的可行性
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
Unverified2022年DeepMind发布了TALM，Meta发布了Toolformer，探索让模型自主决定何时调用外部API，但依赖微调76% similarVerifiedDeepMind's AlphaProof combined large language models with Lean 4 in 2024 and used reinforcement learning to self-play in a formal environment to generate and verify proof steps.73% similarUnverifiedAfter 2022, DeepMind's AlphaProof and various large language models began combining neural networks with symbolic reasoning.72% similarUnverified2017年OpenAI与DeepMind分别独立发表论文探索从人类偏好中学习的强化学习方法，2022年InstructGPT论文发表后RLHF成为LLM对齐的主流范式71% similarUnverifiedDeepMind launched the Auto-RT project, combining large language models with the robot control model RT-2, using the LLM as a task planning layer to decompose natural language instructions into low-level action sequences.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/533808API
curl https://kongchang.com/api/v1/knowledge/claims/533808MCP
get_claim(id=533808)