- Rating
- 2
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper studies parametric memory for language agents: how to keep every experience record individually traceable and editable while reading the memory as a whole at constant cost. The proposed RCMF framework stores each decision transition as a provenance-tracked record that contributes an independent additive term to a fixed-shape compiled memory field; reads are produced by a frozen query module and injected into a frozen Qwen3-8B, and records are inserted or removed by adding or subtracting their contributions without retraining. On AppWorld, ALFWorld, and WebShop, with baselines rerun in the same environments, RCMF attains the highest average success (30.96% vs. 27.33% for the strongest baseline); compiled reads stay below 0.16 ms while explicit per-record reads grow to 30.29 ms at 499 records.
Critical strengths
- The unification of record-level editability with constant-cost parametric access holds by construction: each record's contribution is independently attributable and can be added or subtracted exactly, the compiled read equals the explicit per-record sum term by term (Eqs. 12-14), and the query-key decomposition introduces no additional projection (Appendix A.3). Reversible editing, provenance auditing, and fixed-shape reads thus become algebraic properties of the framework -- a substantive contribution relative to Larimar, MemGen, and -mem -- and the main support for the overall assessment.
- The evidence is layered and the comparison fair: four baselines are rerun under the same backbone, environments, and evaluators; ablations isolate state-conditioned addressing as the largest empirical factor (-12.50pp); and field-level shuffles with record-level log-probability interventions (related +0.1901 vs. unrelated +0.0025) support the mechanistic explanation beyond end-to-end scores.
Critical weaknesses
- The headline results lack stability evidence. Table 1 reports single runs on small fixed evaluation sets (168/134/200 tasks) with no repetitions or interval estimates; the margin over the strongest baseline corresponds to only 2-7 tasks per benchmark (AppWorld 48 vs. 41; ALFWorld 52 vs. MemGen's 50), and the 3.63pp average margin is of the same order as the ~3.3pp binomial standard error of a single proportion at n=168, so the stability of the advantage cannot be judged -- this directly limits the effectiveness claim.
- The most distinctive selling points have the weakest evidence. Record-level editing reversibility is supported only algebraically and through one-step log-probability shifts on 20+20 held-out pairs (Eq. 18), with no closed-loop experiment on task success after insertion/removal; "N-independence" covers only read latency and active storage (Table 9), and superposition interference or addressing-accuracy degradation of the fixed-shape field as N grows is never measured behaviorally (the deployment bank holds only 499 records).
Questions for authors
- Are all Table 1 results single runs? Could you provide multi-seed repetitions, or at least paired interval estimates over the evaluation sets (e.g., paired bootstrap), to judge whether the 3.63pp average margin over the strongest baseline exceeds run-to-run variability?
- Have you run (or could you add) an end-to-end editing evaluation: after deleting or replacing several compiled records, does success on the affected tasks change as algebraic reversibility predicts? This is the minimal evidence for the practical utility of record-level editing.
- How many transitions do the deployment memory banks for ALFWorld and WebShop contain, and how many supervised states were used for Writer-Reader training on each? Appendix B.3 fully specifies only the AppWorld instance (366 states, 499 records).
- As N grows well beyond 499, is the addressing quality of the compiled field (related-record log-probability shift or downstream success) preserved, or are only latency and storage constant?
3 comments
Response to Reviewer Nuoj (Part 2)
W2b: Using the same frozen model and evaluation settings, we tested memory growth across 4 nested banks: 401-record Writer–Reader optimization pool, 499 records (adding 98 withheld transitions without weight updates), and 800 / 1600 records (adding 301 and 1101 LLM-generated synthetic variants to the 499-record bank to evaluate performance with larger banks). These variants modify entities or descriptions in training-side transitions while preserving their action semantics, structure, and provenance.
Table 2-2. Task success and retention under memory-bank growth.
| Memory Count | AppWorld Success | Retained Successes from N=401 |
|---|---|---|
| 401 | 44/168 | 44/44 |
| 499 | 48/168 | 42/44 |
| 800 | 50/168 | 41/44 |
| 1600 | 50/168 | 43/44 |
Retention counts how many of the 44 tasks solved at N=401 remain successful as the bank grows, exposing regressions despite higher overall success. All learned components remain frozen. Performance improves beyond the original Writer–Reader training-bank size, while most previously solved tasks are retained. These results provide behavioral evidence that useful memory access survives substantial synthetic interference.
Q1: Yes. All results in the original Table 1 were based on a single run. Details can be found in W1 and Tables 1-1 and 1-2.
Q2: Addressed in W2a and Table 2-1.
Q3: As described in Appendix B.3, AppWorld uses 366 supervised decision states and a memory pool of 401 transitions from 29 training-split tasks. 8 additional tasks from the same training split provide 98 held-out transitions. After Writer–Reader optimization, the 98 held-out transitions are added to the memory field without further training, yielding 499 deployment records.
Table 5-1 provides the corresponding statistics for ALFWorld and WebShop. The same Writer–Reader training framework and optimization settings are used across benchmarks, while data-dependent quantities, such as the number of training units and optimizer updates, vary accordingly.
Table 5-1. Memory construction and Writer–Reader training statistics.
| Parameter | AppWorld | ALFWorld | WebShop |
|---|---|---|---|
| Tasks for training | 29 | 59 | 101 |
| Transitions from training tasks | 401 | 408 | 411 |
| Eligible supervised decision states | 366 | 390 | 384 |
| Held-out tasks | 8 | 14 | 23 |
| Transitions from held-out tasks | 98 | 99 | 105 |
| Total deployment transitions | 499 | 507 | 516 |
Q4: Addressed in W2b and Table 2-2.
Please respond to the author rebuttal
Dear Reviewer Nuoj, could you please respond to the author's rebuttal? Thanks!
Response to Reviewer Nuoj (Part 1)
W1: Thank you for the constructive feedback. The final RCMF design was completed only one month before submission, leaving insufficient time for repeated runs. We continued these experiments after submission and have now obtained three runs for all five methods (Table 1-1). All applicable training stages were rerun from scratch. RCMF achieves the highest mean on every reported metric. Its lowest observed success rate also exceeds the strongest baseline’s highest observed rate on each benchmark, although the ALFWorld margin remains small.
Table 1-1. Effectiveness across three runs (mean ± SD).
Table 1-1 measures run-to-run variability, whereas Table 1-2 assesses uncertainty in the performance differences arising from task sampling. We compute paired 95% bootstrap confidence intervals by jointly resampling the same evaluation tasks for RCMF and the strongest original baseline.
Table 1-2. Paired uncertainty against the strongest original baselines.
The paired intervals exclude zero for AppWorld success and both WebShop metrics, supporting positive task-level differences in the reported runs. The ALFWorld CI reaches zero, leaving its two-task gain statistically uncertain. Overall, repeated runs support consistent improvements, with weaker statistical evidence on ALFWorld.
W2: Thank you for the insightful feedback. We address W2 in two parts: W2a Behavioral Memory Editing and W2b Memory Growth and Interference.
W2a: We conducted behavioral editing on 20 related and 20 unrelated AppWorld tasks using records from the 98 transitions withheld, extending the original log-probability probes to end-to-end task outcomes. Related tasks are grouped by correctness of target action under Background, regardless of final task success. Each task uses the same model, decision state, and source record under 4 conditions: Background (401 records), Insert with Original (adding the original record), Replace with Misleading (replacing the original record with semantically misleading version), and Delete to Background (removing inserted record). Original and misleading records never coexist.
We report A (percentage of tasks for which correct action is executed at matched decision state) and T (full-task success from independent rollouts). Observed rates are in %; brackets give task-paired 95% bootstrap CIs for differences from Background (pp).
Table 2-1. Effects of memory editing on action accuracy and task success.
Inserting original record corrects 8/10 wrong related actions while preserving correct ones. Replacing it with misleading content disrupts related decisions, whereas unrelated tasks remain largely unaffected. Deletion restores Background performance. These results provide behavioral evidence of memory specificity beyond log-probability probes.