- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies how tool-using LLM agents can continue safely after restoring an earlier checkpoint. Incomplete recovery can leave permissions and task records inconsistent with restored files and conversation, or cause already completed external actions, such as sending an email, to be repeated.
The main contribution is an explicit recovery rule: internal task state returns to the checkpoint, while records of completed external actions are preserved. The proposed Closed-World Checkpoint implements this rule by restoring the agent's registered internal task state while retaining effect receipts. It coordinates these steps before allowing tool use to resume.
Experiments across different execution settings show that CWC helps prevent unauthorized actions, incorrect completion reports, and repeated external operations in the tested settings. However, if an external action succeeds before its completion record is saved, CWC alone may still repeat it, so additional mechanisms are needed to make retries safe.
Critical strengths
The ablation experiments clearly show the different roles of side-store recovery and receipt preservation. Removing side-store recovery brings back unauthorized deletion, while removing receipts causes repeated external operations; in each case, protection against the other failure remains intact. Section 4.4 also reports a crash scenario in which CWC alone fails, helping clarify the method's limitations. The ablations make the proposed mechanism more convincing.
Critical weaknesses
CWC's added research contribution is not sufficiently established. Section 4.6 and Appendix G report identical outcomes for CWC and FS when recovery state and protective mechanisms are matched. The origin and construction of FS, the specific hypothesis tested by this comparison, and how its results support CWC's contribution need clearer explanation. This leaves unclear how much the paper advances existing recovery ideas through its recovery rule or implementation. The paper does not yet provide a convincing case for CWC’s added research value.
Questions for authors
1.Section 2.1 defines as the agent's effective constraints/obligations derived from and ; how is the "do not send" constraint represented in if the user instruction "draft the email but do not send it" exists only in ? Does this assume that all relevant constraints/obligations in are recorded in or , or should also depend on ?
2.Please clarify the origin and recovery procedure of FS and how it differs from CWC. Given their identical outcomes under matched recovery and continuation settings, what does this comparison establish about CWC's added research contribution?