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.
arXiv:2607. 23722v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes.
arXiv:2607. 16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.
arXiv:2604. 13072v2 Announce Type: replace-cross Abstract: OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments.
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%.
arXiv:2608. 12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation.
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.
BuildBench introduces a realistic benchmark for evaluating large language model agents on the task of compiling open‑source software (OSS). It includes diverse OSS projects that lack clear build instructions, have undocumented dependencies, and may require source patching or script modification. The authors also present OSS‑BUILD‑AGENT, a baseline LLM‑based agent that retrieves build instructions effectively and achieves state‑of‑the‑art performance on the benchmark.
arXiv:2609.35811v1 Announce Type: cross Abstract: Tool retrieval is a critical bottleneck for LLM-based agents operating over large, heterogeneous API ecosystems. Existing approaches face an inherent...
arXiv:2609.06059v1 Announce Type: new Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to a...
arXiv:2609.06124v1 Announce Type: new Abstract: High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-l...
arXiv:2607. 16617v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts.
EDGEGEN is a synthetic task generation framework that extracts compliance rules from a tool‑calling agent’s specification to create database‑grounded edge‑case tasks that violate those rules. By combining EdgeGen with existing synthetic data generation methods, it forms a fully automated closed‑loop system that requires no human annotation. Experiments show that finetuning on EdgeGen data improves performance by 2–42 % on the tau2bench airline domain, while harness optimization yields 10–30 % gains over human‑curated and base harnesses for the Gemma‑4‑e4b model.