Catch Your Agent Inventing Tool Results (Before Your Users Do)

说明与用途

通过执行器侧账本审计代理工具调用，可检测伪造或误引用的结果，确保仅报告真实执行。

问题

AI agents can fabricate or misquote tool results, leading to hallucinated outcomes that pass transcript reviews.

结果

Auditing against an executor-side ledger reliably uncovers fabricated or misquoted tool results, ensuring agents only report genuine executions.

工作流

• 1. Record every tool dispatch in a ledger: tool_call_id → {tool, args, raw result}.
• 2. After agent run, extract all factual claims about tool outcomes, noting referenced call IDs and asserted results.
• 3. For each claim, check ledger: if call ID missing → FABRICATED; if result mismatches → MISQUOTED; else OK.
• 4. Flag any FABRICATED or MISQUOTED findings for review.
• 5. Repeat audit after every run that touches real resources.

证据

Audit them against an executor-side ledger.

来源

Your executor records every dispatch: tool_call_id → {tool, args, raw result} in a ledger the agent can't write to.

来源