IBM 推出代理決策閘道研究 - JevAct:在代理與工具之間加入執行閘道,透過 LLM 轉域政策為程式檢查與是非問題。
- 效能提升:在 τ²-bench Telecom 上,Opus 4.6 的成功率從 39.5% 飆升至 80.7%。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Banger paper from IBM on decision gates for agents.
They add a runtime gate to tool-using agents and keep the models and tools the same.
JevAct is a check that sits between the agent and its tools. An LLM first turns the domain policy into code checks and yes/no questions. Before a selected tool call runs, the code checks the facts in the tool records, and a Jev-like decision model answers the questions about the conversation. If the call fails a check, it goes back to the agent with feedback so the agent can revise it.
On τ²-bench Telecom, Opus 4.6's success across all three runs rose from 39.5% to 80.7%.
On Telecom, all eight agents improved by 16.9 points on average in three-run success. All nine improved on BFCL. Airline results were smaller and mixed.
They show that the gains come from the harness.
Chat with Paper: https://t.co/73KKMxZDXJ