- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
PagedMem is an external memory system for frozen LLM agents. It organizes past reflections into semantic pages containing headers, summaries, and supporting records. Memory is initially exposed at an abstract level and progressively expanded or replaced in response to execution deficits, while task feedback drives subsequent maintenance. Experiments on ALFWorld with three backbones report higher success rates and fewer invalid actions than ReAct, AWM, and MemP.
Critical strengths
-
The paper addresses a consequential problem with a clear design rationale. Overly specific historical experience can misguide execution in a different environment. Separating memory representation from exposure granularity, and progressively revealing details, offers a plausible approach to reducing this interference. This problem formulation and design rationale are the strongest conceptual merits of the paper.
-
The reported behavioral improvements are consistent across backbones. The complete system improves success rates and substantially reduces invalid actions on all three backbones. For example, on Qwen, invalid actions decrease from MemP’s 67/46 on Seen/Unseen to 11/4. These results suggest practical potential and make the approach worth further investigation.
Critical weaknesses
-
The baseline comparison is insufficient. The paper compares only against ReAct, AWM, and MemP. Since ReAct has no persistent memory, this amounts to only two memory-based competitors. Directly relevant dynamic memory methods are missing, and I do not consider the current comparisons sufficient to establish PagedMem’s relative advantage. This is a major concern affecting my recommendation. Relevant additional baselines include AdaMem[1], AutoGuide[2], ExpeL[3], ReasoningBank[4] and some recent experience memory works.
-
The ablations do not adequately validate the central mechanism. Removing hierarchical representation simultaneously changes memory content, summarization quality, and text length, preventing attribution of the performance difference specifically to granularity. Without controls such as L1-only guidance, length-matched summaries, and scheduled expansion, the independent value of execution-triggered disclosure remains unclear. This weakens the claim that granularity decoupling is the principal source of improvement.
[1]https://arxiv.org/abs/2606.05684
[2]https://arxiv.org/abs/2403.08978
Questions for authors
-
Does PagedMem retain its advantage over directly relevant methods such as AdaMEM and AutoGuide when backbones, experience sources, and interaction budgets are aligned? Please provide comparative evidence.
-
Does execution-triggered progressive disclosure provide an independent benefit over L1-only guidance, length-matched summaries, and scheduled expansion?