#tool-use2 articles

2 articles

AINeutralarXiv – CS AI · 5h ago2

🧠

ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context

Researchers released ASTRA-bench, a new benchmark for evaluating AI agents' ability to handle complex, multi-step reasoning with personal context and tool usage. Testing revealed that current state-of-the-art models like Claude-4.5-Opus and DeepSeek-V3.2 show significant performance degradation in high-complexity scenarios.

AIBullisharXiv – CS AI · 5h ago1

🧠

CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification

Researchers introduce CoVe, a framework for training interactive tool-use AI agents that uses constraint-guided verification to generate high-quality training data. The compact CoVe-4B model achieves competitive performance with models 17 times larger on benchmark tests, with the team open-sourcing code, models, and 12K training trajectories.