Google Research released ToolGrad, an ACL 2026 Findings framework that generates tool-use datasets by building a verified API chain first and then writing the matching user query, reaching a 99.8% pas…
Google researchers Zhongyi Zhou and Ruofei Du introduced ToolGrad, a data generation framework that reverses the traditional tool-use dataset paradigm by generating ground-truth tool-use chains before…
A new lossless wire format called a2acompress cuts token usage by 36.6% on real cl100k_base tokens for agent-to-agent handoffs, reducing 140,661 raw tokens to 89,235 full-cost tokens across 196 held-o…
Researchers from multiple institutions, including Swarnadeep Bhar and Nicholas Asher, introduced COCORELI, a modular architecture that enforces missing information as a precondition for action, blocki…
Qin et al. introduced ToolLLM at ICLR 2024, enabling large language models to master 16,464 real-world REST APIs via ToolBench built from RapidAPI without human labels, using a depth-first search with…
Researchers deployed an automated pipeline to optimize skill descriptions for an enterprise AI agent, achieving 79.2% F1 accuracy versus 79.4% for manual tuning while reducing engineering effort per s…
Researchers have developed ToolSense, an open-source diagnostic framework that automatically generates three benchmarks to audit whether large language models truly understand their parametric tool kn…