TabMWP-Hard

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

01:36

2026-08-26

tool-use-smith.github.io

artificial-intelligence

Joint Optimization of Tool Creation and Use for Large Language Model Agents

Appier AI Research and National Taiwan University introduced SMITH (Schema-grounded Multi-task Iterative Tool Honing), a reinforcement learning framework that jointly trains tool creation and tool use…

01:36

2026-08-26

arxiv.org

artificial-intelligence

Training LLMs to write tools generalized beyond self use

Researchers propose SMITH (Schema-grounded Multi-task Iterative Tool Honing), a reinforcement learning framework that jointly trains tool creation and tool use in a single policy, enabling a 4B Qwen3 …

// co-occurs with top 8 entities

SMITH 2 Qwen3 2 GQA 2 LFM-2.5-350M 1 Qwen3-30B-A3B 1 Appier AI Research 1 National Taiwan University 1 DAPO 1

// topics top 5 topics

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