Google Research has released ToolGrad, an ACL 2026 Findings framework that inverts tool-use dataset generation: it builds a verified API chain first, then writes the matching user query. Guided by textual "gradients" from a 4-module propose-execute-select-update loop, ToolGrad reaches a 99.8% pass rate on ToolBench versus 63.8% for DFS search. Gemma-3-12B fine-tuned on only 500 samples scores 83.1 on BFCL, next to Gemini 2.5 Pro at 83.2. Code, dataset, and models are public under Apache-2.0.
The post Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation appeared first on MarkTechPost.
source & further reading
marktechpost.com — original article
Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster
NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100
OpenAI Launches the Agents API in Public Beta, Putting the Codex Harness Behind One API Call