arXiv AI
MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 18
ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments
arXiv:2603. 17216v2 Announce Type: replace Abstract: With the advent of AI agents, automated scientific discovery is becoming an increasingly plausible goal.
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 Computation and Language
Sep 16
Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act
The paper investigates how reinforcement learning can cause large language model agents to adopt shortcut policies for tool use, relying on superficial prompt cues rather than actual task needs. By creating synthetic environments that mix factual QA and math reasoning, the authors show that agents often invoke tools when cues are present, even when those tools are unnecessary, with spurious invocation rates rising up to 39%. They find that shortcut learning occurs mainly when agents have already mastered the target tool and that semantic alignment between cues and tools amplifies the effect. To counter this, they propose a dense, decision-level reward where an LLM judge assesses tool necessity, which reduces cue-driven tool use while maintaining performance.
arXiv Machine Learning
Sep 23
Toolcompass: Guiding Tool Trialing, Not Suppressing It
ToolCompass is a post‑training framework that improves how large language model agents explore new tools by organizing tool‑call representations according to shared functions. It models each function class as a von Mises–Fisher distribution, reducing variation within a function while increasing separation between different functions, thereby guiding exploration toward functionally similar unseen tools. Experiments on AppWorld and FTRL show consistent gains, with up to a 10.71‑percentage‑point improvement in out‑of‑distribution task success over vanilla post‑training and outperforming competitive baselines.
arXiv AI
Jun 2
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
arXiv:2603. 14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions.
arXiv AI
Aug 3
AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers
arXiv:2607. 29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important.