- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes AFS, an agent-native file system designed to improve file access efficiency for LLM agents. The framework uses a Main Agent for reasoning and multiple parallel File Agents for retrieving relevant evidence from files. It combines reusable per-file KV caches, continuous batching, and asynchronous evidence retrieval to reduce repeated computation and the amount of context passed to the Main Agent.
Critical strengths
-
The use of a fixed file prefix allows the system to reuse KV caches across different queries, reducing repeated prefill computation and improving file inspection efficiency.
-
The span selection mechanism substantially reduces the amount of evidence passed to the Main Agent. The ablation results show improvements in answer accuracy while using significantly fewer evidence tokens compared to full-file loading.
Critical weaknesses
-
The baseline comparisons are not entirely convincing. AFS essentially uses a main agent and multiple parallel file agents for evidence retrieval, but the existing baselines are mainly based on sequential retrieval or conventional search tools. A more meaningful comparison would be against a standard multi-agent framework where a main agent delegates file inspection to multiple subagents in parallel. Without such a baseline, it is difficult to tell how much of the improvement comes from the proposed AFS design and how much simply comes from parallelizing the retrieval process.
-
The methods explore substantially different numbers of files. For example, on LoCoMo, AFS inspects 27.78 files per question, compared to only 4.77 for Dynamic RAG and 14.37 for Grep-based Harness. This raises the question of whether the performance gains come from more effective evidence retrieval or simply from exploring more files. While the paper reports lower online latency, inspecting more files may also introduce additional computational costs. It would be helpful to compare these methods under similar file exploration or computational budgets to better understand the actual effectiveness and efficiency of AFS.
-
The evaluation is limited to three QA benchmarks: LoCoMo, HotpotQA, and 2WikiMultiHopQA. While these benchmarks test evidence retrieval across documents, they do not fully reflect realistic file-intensive agent workflows. For example, it would be useful to evaluate AFS on code repositories, where agents need to navigate complex file structures and files may be frequently modified during execution. In such dynamic environments, it is unclear whether the proposed approach can still maintain its advantages, especially since its KV cache reuse relies on preprocessed file contents.
-
It is unclear whether AFS can really be considered an agent-native file system. The proposed method mainly uses multiple file agents to retrieve relevant passages, together with existing techniques such as KV caching and continuous batching. This seems closer to a multi-agent retrieval framework than a general file system.
Questions for authors
How is the granularity of source spans determined? The paper does not clearly specify how files are divided into spans or how much surrounding context is included. Have the authors examined how different span sizes affect evidence recall, final answer quality, and retrieval efficiency?
5 comments
Author Rebuttal [Part 2]
W4. What makes AFS an agent-native read design beyond parallel retrieval?
A4. Thank you for your comments. We use "agent native" to describe file access organized around model computation. AFS makes each file independently inspectable and reusable, while the Main Agent maintains its global reasoning history.
A read takes a file identity and an information request and returns source addresses. The runtime resolves these addresses into original text with provenance. Later requests can reuse the fixed file prefix without placing the file after the Main Agent's accumulated history.
Reviewer Qc7g recognizes that "The serving and access mechanisms are concrete." Reviewer bbij also values retrieving "the original text with its source locations" instead of generating summaries. These comments concern the file reading design that we evaluate.
Table 3. File reading mechanisms and their controlled measurements.
| Design | Computational purpose | Supporting evidence |
|---|---|---|
| Fixed file prefix before the changing request | Reuse file input computation independently of the Main Agent's history while resident | Mean time to first token is 919.7 milliseconds cold and 297.7 milliseconds warm |
| Lightweight File Agents on a shared continuously batched service | Execute independent local inspections concurrently | Inspection throughput increases from 2.64 to 4.27 calls per second with one and three workers |
| Source addresses resolved to original records | Avoid regenerating long passages and limit unnecessary source delivery | Delivered source text falls from 27,690 to 892 tokens. Recall is 0.917, and F1 increases from 0.323 to 0.411. |
Retrieval discovers candidate sources. AFS also specifies how a located file is inspected, how its computation is reused, and how original evidence reaches the reasoner while inspection continues. It uses existing cache and batching mechanisms to execute this design. The current implementation covers reading; writes and operating system semantics remain outside the evaluated scope.
Q1. “How is the granularity of source spans determined? The paper does not clearly specify how files are divided into spans or how much surrounding context is included. Have the authors examined how different span sizes affect evidence recall, final answer quality, and retrieval efficiency?”
QA1. Thank you for the question. Each source span is a nonoverlapping group of four lines, with a shorter final group when needed. A File Agent can select multiple spans, including spans that are not adjacent. Four lines therefore defines an addressable unit, not the maximum evidence length.
The resolver returns original text and its locations using the declared expansion rules. LoCoMo includes bounded neighboring context for image sharing records.
Table 4. Span size sensitivity on the same 20 LoCoMo questions.
| Lines per anchor | Answer F1 | Annotated interval recall | Original source tokens delivered to Main Agent |
|---|---|---|---|
| 2 | 0.3011 | 0.5714 | 860 |
| 4 | 0.3706 | 0.6190 | 1,377 |
| 8 | 0.3911 | 0.6190 | 2,104 |
| 16 | 0.3883 | 0.6190 | 2,744 |
We hope these component experiments and the parallel baseline address different parts of the attribution question.
Gentle Reminder
Dear Reviewer qHUQ,
Thank you for your response and for your positive assessment of our work. We have incorporated your feedback into the revised manuscript, and we will continue to improve the paper with respect to your remaining concerns. Please let us know if you have further concerns.
Authors
Author Rebuttal [Part 1]
Thank you for the constructive review and for recognizing the benefits of file prefix reuse and selection that preserves the original source.
A1. Thank you for the suggestion. We added a baseline in which the Main Agent delegates file inspection to parallel subagents. It uses Qwen3.5-9B on the same H200 service as AFS and receives the same questions, prompts, routing summaries, cache preparation, worker limit, and final answering procedure.
The subagents use the same file reader as AFS. They return the same kinds of source addresses, which are expanded into original text using the same rules. The Main Agent selects a batch of file requests and waits for that batch to complete. In AFS, the inspection queue replenishes independently while the Main Agent reasons and can request further focused reads.
Table 1. AFS and parallel subagents with matched readers on the same 20 questions per dataset.
A2. Thank you for the comment. Table 5 in the paper fixes the inspected files, focused requests, and final decoder. It changes only the evidence delivered to the Main Agent.
Reviewer Qc7g calls this "a useful controlled result" and states that it "supports selective delivery of original evidence." We agree with the reviewer's qualification that this experiment alone does not validate the complete architecture. It tests evidence selection with exploration held fixed.
Table 2. Evidence selection with identical file inspection on 100 LoCoMo questions.
At similar text budgets, File Agent selection retains more annotated evidence than dense span selection. Recall is 0.917 compared with 0.510, and F1 is 0.411 compared with 0.383. Relative to complete files, it reduces delivered source text by 96.8% and improves F1. On the 73 questions with evidence annotations, F1 is 0.276 for File Agent selection, 0.209 for dense spans, and 0.237 for complete files.
A3. Thank you for the suggestion. This paper focuses on file reading and evidence acquisition. Evaluating code repositories requires suitable tasks for repository navigation and validation of the final result. We plan to explore this setting in future work. We have clarified this scope in the “Limitations and Future Work” paragraph of Section 6 (Conclusion). The revision specifies that our evaluation covers file reading and evidence acquisition over static corpora and describes what a code repository evaluation would require.