Tool use is older than you think: LaMDA paper casually mentioned it in Jan 2022
soldni · x · 2026-10-15
Researchers debate the history of tool use and RLVR: LaMDA's paper casually mentioned tool calling in January 2022, and self-training LLMs to use tools/search predates 2021. soldni notes OpenAI was likely already experimenting with RLVR back then; lateinteraction argues RLVR is just RL (RLHF is the weirder variant), and early-2021 RL for chain-of-thought would have been remarkable — but the doc in question wasn't that.
Related event: Researchers Trace RLVR's Roots: It's Just RL, and the Idea Isn't New(3 posts)→
More from Research
- Microsoft's SMD distillation hits 4-step generation that beats multi-step diffusion teachers — microsoft · 2026-10-15
- Colossal Uses AI to Rebuild Extinct Genomes and Track Endangered Species — IgorCarron · 2026-10-15
- Thinking Machines ships Dimuon optimizer for LoRA fine-tuning, beats AdamW in fewer steps — simonguozirui · 2026-10-15
- NVIDIA report: agentic setup lets GPT-6 Astra hit 74.8% on RoboLab-120 robot manipulation — YuXiang_IRVL · 2026-10-15
- Bittensor Subnet 55 completes 10M synthetic CRISPR experiments with 248 competing miners — markjeffrey · 2026-10-15
- Logit lens shows Qwen3-1.7B's refusal to be shut down depends on how many layers you train — Sauers_ · 2026-10-15