Entity · technique

Knowledge-Augmented Tool Execution

techniqueactiveknowledge-augmented-tool-execution-423f65f0·1 events·first seen Jun 10, 2026

Aliases: Knowledge-Augmented Tool Execution

Co-occurring entities

More like this (12)

Emergent Tool Use tool-augmented language agents Tool-Integrated Reasoning Knowledge Assist Reference-Augmented Training tool-calling agents From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability How AI Agents Reshape Knowledge Work: Autonomy, Efficiency, and Scope LMs as Task-Specific Knowledge Bases: An Interpretability Analysis Knowledge Seeding Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

Recent events (1)

6arXiv · cs.CL·Jun 10, 2026·source ↗

KATE framework improves LLM tool calling via experiential knowledge integration and parallel reasoning

Researchers present KATE (Knowledge-Augmented Tool Execution), a framework addressing LLM failures in multi-step tool use by systematically studying knowledge acquisition, activation, and internalization. Key findings include that instance-level experiential knowledge outperforms abstract intent-level knowledge, that expanding reasoning width via parallel sampling with aggregation beats deeper chain-of-thought, and that reinforcement learning outperforms supervised fine-tuning for knowledge internalization. KATE is evaluated on BFCL-V3 and AppWorld benchmarks, showing consistent improvements over strong baselines across model scales.

Evaluation and Benchmarking Agent and Tool Ecosystem BFCL-V3 AppWorld Knowledge-Augmented Tool Execution +1 more