UniToolCall introduces a unified framework for tool-use in large language model agents, standardizing toolset construction, dataset generation, and evaluation. The framework aggregates over 22,000 tools and creates a hybrid training corpus of more than 390,000 instances by combining ten public datasets with synthetically generated, structurally controlled trajectories. It models diverse interaction patterns—single‑hop vs. multi‑hop, single‑turn vs. multi‑turn, serial vs. parallel execution—and adds an Anchor Linkage mechanism to enforce cross‑turn dependencies, while converting seven public benchmarks into a common Query–Action–Observation–Answer format for fine‑grained evaluation.
By Yijuan Liang, Xinghao Chen, Yifan Ge, Ziyi Wu, Hao Wu, Changyu Zeng, Wei Xing, Xiaoyu Shen
Agent Seer is a pipeline that automatically synthesizes realistic evaluation scenarios for AI agents that use external tools, using only the tool’s specification (function names, natural‑language descriptions, and typed parameter schemas). Starting from a single Model Context Protocol (MCP) specification, it enriches raw schemas, generates graded scenarios with synthetic tool outputs, and expands them into mock‑data‑grounded multi‑turn dialogues that demonstrate strong tool‑calling correctness and conversational coherence. Across seven diverse MCP specifications, the pipeline achieves high quality, with parameter‑schema complexity emerging as the main driver of quality variation and argument‑value accuracy identified as the dominant failure mode.
By Harish Karumuri, Mahesh Vemula, David Lopes Pegna
The paper introduces KOPA-Bench, a benchmark of 145 real-world tasks that evaluate multi-step tool‑calling over Korean open public APIs. It also presents EDGE, a data‑synthesis method that builds an execution‑grounded dynamic graph to generate executable multi‑step trajectories, and shows that a fine‑tuned 9B model performs nearly as well as an untuned 27B model on KOPA‑Bench and the BFCL benchmark.
By Dain Kim, Eungi Cho, Kyumin Kim, Shinyeong Noh, Kyuseong Lim
arXiv:2609.37233v1 Announce Type: cross
Abstract: Datalog underpins reasoning tasks such as program analysis, but its programs are hard to write. Existing synthesizers automate this task but require...
By Yuan Li, Hanyun Jiang, Guowei Tian, Chengpeng Wang, Peisen Yao
arXiv:2607. 02771v1 Announce Type: new Abstract: Leadership computing facilities steward large-scale scientific datasets that routinely require substantial transformation before serving as AI training data.
By Sean R. Wilkinson, Valentine G. Anantharaj, Jong Youl Choi, Ketan Maheshwari, Marshall McDonnell, Massimiliano Lupo Pasini, Polina Shpilker, Renan Souza, Patrick Widener, Sarp Oral, Wesley Brewer
arXiv:2606. 31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery.
By Keyu Zhao, Lingyan Kong, Fengli Xu, Yong Li
arXiv:2606. 07001v1 Announce Type: cross Abstract: High-quality training data is essential to large language models (LLMs) and typically requires extensive and costly manual curation.
By Chao Deng, Shaolei Zhang, Ju Fan, Xiaoyong Du
The paper introduces Tool Primitives, a design that replaces rigid API schemas with natural language interfaces for tool calling, enabling seamless inter-tool communication. It builds ToolFace, a repository of over 25,000 functions that LLMs can dynamically retrieve, and HEART, a harness engineering framework that orchestrates tool use with planning, routing, and verification. Experiments show HEART outperforms fine‑tuned models and leading commercial LLMs while cutting API costs by up to 85%.
By Haibo Jin, Suijin Wang, Xucheng Yu, Haojing Luo, Haohan Wang
arXiv:2606. 10087v1 Announce Type: cross Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats.
By Ankit Gupta, Aditya Prasad, Rameswar Panda
arXiv:2604. 18543v4 Announce Type: replace Abstract: Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale.
By Xirui Li, Ming Li, Ion Stoica, Cho-Jui Hsieh, Tianyi Zhou
arXiv:2607. 18816v1 Announce Type: cross Abstract: LLM-powered agents increasingly tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts.
By Eden Wu, Sonia Castelo, Yurong Liu, Cl\'audio T. Silva, Juliana Freire
arXiv:2608. 11022v1 Announce Type: cross Abstract: Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters, limitations, and intended use.
By Nicola Giuseppe Marchioro, Gabriele Padovani, Amal Gueroudji, Rafael Ferreira da Silva, Wesley Brewer, Valentine Anantharaj, Sandro Fiore, Renan Souza