arXiv AI
Jul 21
Environment-free Synthetic Data Generation for API-Calling Agents
arXiv:2607. 16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.
Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
Related stories
arXiv AI
Sep 3
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
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.
arXiv AI
Sep 7
Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe
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 AI
Sep 3
Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
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%.
Hugging Face Trending Papers
3d ago
ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs...
arXiv AI
Oct 12
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
The paper introduces RobustBench‑TC, a benchmark that tests tool‑use language agents under 22 real‑world perturbations affecting observations, actions, rewards, and transitions. Experiments on 21 models show that observation noise has minimal impact, while reward‑relevant and transition noise drastically reduce accuracy, and model size alone does not mitigate these gaps. The authors propose ToolRL‑DR, a domain‑randomized reinforcement‑learning recipe that improves robustness, retaining most clean accuracy and narrowing performance gaps even on unseen transition perturbations.
arXiv Computation and Language
Oct 7
Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine
arXiv:2610.07070v1 Announce Type: new Abstract: Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool call...
arXiv AI
Sep 30
Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning
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 AI
Sep 1
SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning
SimCRAFT is a model‑agnostic framework that distills remote sensing orchestration into a compact 7B‑scale model. It creates a large, constraint‑validated workflow planning corpus (SimRS‑14k) using a multi‑agent synthesis engine and a Mock Execution Engine, then fine‑tunes the model with Contextual Retrieval‑Augmented Fine‑Tuning (CRAFT) to reason analogically. Experiments show SimCRAFT‑7B outperforms open‑weight LLMs and rivals advanced closed‑source models, providing a lightweight, efficient baseline for autonomous remote sensing deployment.
arXiv AI
Oct 15
Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
arXiv:2610.16867v1 Announce Type: cross Abstract: Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were ach...
arXiv AI
Jul 28
E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios
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 Machine Learning
Aug 12
FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
arXiv:2608. 10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures.