- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes KIM, an implicit memory framework that converts successful interaction trajectories into state-conditioned low-rank parameter adjustments. KIM learns local adjustments for individual decision states, consolidates them into a shared memory field, and dynamically refreshes the resulting intervention during tool interaction. Experiments on seven reasoning benchmarks show substantial gains over the evaluated textual-memory methods and further improvements when KIM is applied to a tool-trained policy.
Critical strengths
- The state-conditioned memory field provides a novel way to consolidate trajectory-specific experience into dynamically activated parameter adjustments.
- KIM achieves substantial average gains across seven benchmarks and improves both instruction-tuned and tool-trained host policies.
- The component ablations clearly examine the roles of general memory, contextual memory, the joint field, and state refresh.
Critical weaknesses
- The main contextual memory bank is selected using the evaluation queries themselves, so the reported results do not cleanly establish generalization to unseen queries.
- The comparison with textual-memory baselines does not isolate the contribution of the contextual field, since KIM additionally uses a general tool-use adapter trained on approximately 54k trajectories and the methods do not receive identical data access.
- The evaluation is limited to 3B-scale backbones, while the absence of multiple training seeds leaves scalability and optimization stability unclear.
Questions for authors
- How many of the 347 overlapping trajectories enter the final 3,609-trajectory contextual bank, and can the authors report results using an independently constructed, overlap-free bank?
- Could the authors compare KIM with textual-memory methods using the same general tool-trained reference policy and the same non-overlapping trajectory pool, thereby isolating the contribution of the contextual field?
- Does KIM retain its gains on 7B/8B backbones and across multiple training seeds?
4 comments
Response to BSdj (2/2)
W3.1. The evaluation is limited to 3B-scale backbones,
We extended the evaluation beyond Qwen2.5-3B to 8B backbones from two model families: Qwen3-8B and Llama-3.1-8B-Instruct. On each, we compared KIM with full-bank RAG on the original seven benchmarks.
| Backbone | Method | GSM8K | MATH500 | AIME24 | HotpotQA | 2Wiki | MuSiQue | Bamboogle | Macro avg. (%) |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3-8B | Full-bank RAG | 92.00 | 80.00 | 26.67 | 49.50 | 45.50 | 21.00 | 50.40 | 52.15 |
| Qwen3-8B | KIM | 93.50 | 85.00 | 40.00 | 51.00 | 42.00 | 21.00 | 48.80 | 54.47 |
| Llama-3.1-8B-Instruct | Full-bank RAG | 82.00 | 55.50 | 10.00 | 46.50 | 31.00 | 20.50 | 44.80 | 41.47 |
| Llama-3.1-8B-Instruct | KIM | 82.00 | 58.50 | 13.33 | 48.00 | 44.00 | 16.00 | 51.20 | 44.72 |
The advantage over full-bank RAG extends beyond the original 3B backbone: KIM leads by 2.32 percentage points on Qwen3-8B and 3.25 points on Llama-3.1-8B-Instruct in seven-benchmark macro-average accuracy.
W3.2. while the absence of multiple training seeds leaves scalability and optimization stability unclear.
We fix the 3B tool-trained reference policy, writing bank, training examples, and evaluation protocol. Only KIM’s initialization and training-example order vary. For each seed, we evaluate step 5,100 and compare its macro-average accuracy with the baseline reported in Table 2 with the field readout off (W2.1).
| Method / training seed | GSM8K | MATH500 | AIME24 | HotpotQA | 2Wiki | MuSiQue | Bamboogle | Macro avg. (%) |
|---|---|---|---|---|---|---|---|---|
| Field readout off (Table 2) | 70.00 | 61.00 | 6.67 | 31.00 | 26.00 | 9.00 | 16.00 | 31.38 |
| KIM, 20260725 (paper) | 77.00 | 62.00 | 16.67 | 43.50 | 38.50 | 18.00 | 35.20 | 41.55 |
| KIM, 20260726 | 74.00 | 60.50 | 16.67 | 45.50 | 37.50 | 17.00 | 36.80 | 41.14 |
| KIM, 20260727 | 78.50 | 63.00 | 16.67 | 42.00 | 40.50 | 19.00 | 33.60 | 41.90 |
Across the three training seeds, KIM averaged 41.53% macro accuracy (sample SD: 0.38 percentage points).
Q1.1. How many of the 347 overlapping trajectories enter the final 3,609-trajectory contextual bank,
None. We excluded all 347 exact question overlaps before training and bank construction, so none entered the final bank of 3,609 trajectories. See our response to Reviewer e7qy (part 1/3, W1) for the separate experiment that added these 347 trajectories to a random bank.
Q1.2. and can the authors report results using an independently constructed, overlap-free bank?
W2.3 evaluates a bank of 3,609 independently sampled trajectories with exact evaluation overlaps excluded. KIM’s seven-benchmark macro-average accuracy is 40.36%, close to the 41.55% in the main experiment (W2.1), suggesting that overall performance on these benchmarks is not very sensitive to how the bank is constructed.
Q2. Could the authors compare KIM with textual-memory methods using the same general tool-trained reference policy and the same non-overlapping trajectory pool, thereby isolating the contribution of the contextual field?
W2.3 gives both methods the same tool-trained reference policy and overlap-free bank. KIM still outperforms adapter-equipped RAG (40.36% vs. 36.62% macro-average accuracy). W2.1 isolates the readout itself: enabling it raises macro-average accuracy by 10.17 percentage points with the adapter held fixed.
Q3.1. Does KIM retain its gains on 7B/8B backbones
In W3.1, we compared KIM with full-bank RAG on two 8B backbones. KIM retained its advantage on both, leading by 2.32 percentage points on Qwen3-8B and 3.25 on Llama-3.1-8B-Instruct in seven-benchmark macro-average accuracy.
Q3.2. and across multiple training seeds?
In W3.2, seven-benchmark macro-average accuracy ranged from 41.14% to 41.90% across three training seeds. All three exceeded the 31.38% reported with the field readout off in Table 2.
Thank you for encouraging us to test whether the gains hold across backbones and training seeds.
Best regards,
The authors
Thanks for the additional experiments. They address my main concerns, so I'll raise my score from 2 to 3.
Thank You for Your Feedback
Dear Reviewer BSdj,
Thank you very much for taking the time to revisit our response and reconsider your assessment. We greatly appreciate your constructive feedback and positive reassessment of our work. Your comments have helped us strengthen the generalization experiments, clarify the baseline comparisons, and improve the empirical evaluation and presentation of our work.
With sincere appreciation,
All Authors
Response to BSdj (1/2)
Dear Reviewer BSdj,
Thank you for recognizing the design of the state-conditioned memory field and KIM’s gains on both instruction-tuned and tool-trained models. We address each concern below.
The main experiment used 3,609 trajectories selected by similarity to the evaluation questions. To evaluate KIM on unseen queries, we exclude exact question overlaps and randomly sample 3,609 Tool-Star trajectories for RAG and KIM, without ranking them by similarity to the evaluation questions. All three methods use the same tool budget and judge. We report accuracy (%) on held-out GSM8K and HotpotQA questions and on four external benchmarks.
KIM scores higher than both baselines on all six benchmarks. Its macro-average accuracy is 8.11 percentage points above adapter-equipped RAG on the same bank and 5.60 points above the tool-trained reference policy without the field.
Table 2 holds the tool-trained reference policy and the memory bank fixed and varies only whether the field readout is enabled.
With the same tool-use adapter, enabling the field readout raises seven-benchmark macro-average accuracy from 31.38% to 41.55%. This isolates a gain of 10.17 percentage points from reading contextual memory.
The main experiment uses roughly 54k historical trajectories to train the general tool-use adapter. To test the effect of training-pool size, we keep the RAG retrieval bank and training steps fixed and train its adapter on either the filtered large pool or a random subset of 3.6k trajectories. KIM (small training pool) uses only those 3.6k trajectories for adapter training, continuation and preference supervision, and memory writes.
When both training and memory writes are limited to 3.6k trajectories, KIM achieves 39.05% macro-average accuracy across the seven benchmarks, compared with 41.55% in the main experiment. KIM thus approaches its main result without access to the full 54k training pool.
RAG and KIM use the same frozen step-3,700 tool-trained reference policy, the same random bank of 3,609 trajectories with exact evaluation overlaps excluded, and the same tool budget. RAG retrieves four trajectories per question as text examples; KIM writes the bank into its field and reads from it at the current interaction state.
With matched data access and tool budgets, KIM scores 40.36% in seven-benchmark macro-average accuracy, above the 36.62% for adapter-equipped RAG on the same bank in the count-adjusted cross-machine summary. RAG scores higher on GSM8K; KIM scores higher on the other six benchmarks.