DART-SD

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

20:26

2026-09-22

cryptobriefing.com

ai-agents

Perplexity.AI reduces tool-call failures by 21% with new model training approach

Perplexity.AI deployed a new self-distillation training method that reduced tool-call failures by 21.2% in live testing, addressing a persistent problem in agentic AI where models call the wrong tool,…

04:00

2026-08-20

machinebrief.com

artificial-intelligence

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

A new framework called DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation) improves multi-turn tool-calling in large language models by shifting from full-trajectory imitation …

// co-occurs with top 7 entities

arXiv 1 Large Language Models 1 Perplexity.AI 1 FRAMES benchmark 1 Google 1 OpenAI 1 ChatGPT 1

// topics top 6 topics

artificial intelligence 2 ai agents 2 machine learning 1 large language models 1 ai search 1 ai research 1