- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Competitive Context Compression (C³), a training approach for agent memory compressors. During training, multiple independent agent histories are placed in one prompt and compressed under a shared output budget, without fixed per-history quotas. GRPO combines downstream task success with a validity bonus, and a curriculum introduces histories from later compaction events. Deployment compresses one history at a time. Experiments report improved task success on SWE-bench Verified and BrowseComp-Plus over single-history GRPO.
Critical strengths
The paper addresses a useful problem and reports improvements in downstream task success across two agent domains while retaining single-history deployment. Table 2 includes single-history and joint training both with and without the budget criterion, providing preliminary evidence that the combined training configuration is useful. These results make the training approach worth investigating.
Critical weaknesses
-
The evidence does not adequately connect the motivating problem to the proposed competition mechanism. The Introduction motivates adaptive retention by observing that histories of similar length can have different memory requirements. However, an independently applied compressor can also adapt its memory length and content to each input. Figure 1 demonstrates relative output shortening for three arithmetic questions, and Figure 3 examines memory-length dynamics. These observations establish shortening, but do not establish the proposed connection between shared capacity and better information selection. Table 2 demonstrates an improvement for the complete configuration, but does not resolve this explanatory gap. Section 6 explicitly acknowledges that the results do not establish how capacity is allocated across histories. It remains unclear how putting independent histories in the same prompt helps the compressor decide what each history needs to retain. The reported results do not show whether joint training improves performance by preserving this information more effectively.
-
The empirical advantage over independent compression is insufficiently established given the observed budget sensitivity. Figure 4 shows that changing the three-history budget from 1,800 to 1,400 tokens increases success from 38.00% to 51.40%. This makes budget selection consequential to interpreting the comparison. However, the single-history budgeted baseline is reported at one calibrated budget, without a corresponding sensitivity analysis. Matching the initial budget-hit rate is a reasonable calibration procedure, but does not establish that the independent baseline has a comparably effective operating point. These limitations prevent me from confidently attributing the advantage to joint shared-budget training rather than to the particular configurations compared.
Questions for authors
-
What evidence supports the connection between heterogeneous memory requirements and the benefit of shared-budget competition? In particular, is there evidence distinguishing flexible allocation from simply applying compression pressure within a joint prompt?
-
How was the target initial budget-hit rate selected, and what data were used for that selection? Were other budgets evaluated for the single-history baseline, and how robust is the joint-training advantage across those choices?
3 comments
Response to Reviewer uyub (2/2)
How was the target initial budget-hit rate selected, and what data were used for that selection? Were other budgets evaluated for the single-history baseline, and how robust is the joint-training advantage across those choices?
Calibration data and target. We follow the shared-context training setup of Batched Contextual Reinforcement [1] and target an initial budget-hit rate of 30%, the fraction of the initial compressor's untruncated outputs that exceed the budget. We calibrated the budget on SWE-smith training histories. We collected each history up to the turn at which the agent's context reached the 4,096-token compaction threshold, randomly grouped three histories into each prompt, and used the initial compressor, Qwen3.5-9B, to generate untruncated memories. We then chose the shared budget that about 30% of these joint outputs exceed.
Single-history baselines. We trained the single-history baseline with two settings, a budget calibrated to the same 30% target (814 tokens) and no budget. Joint training with the shared budget scores higher than both on SWE-bench Verified, with both seeds.
| Configuration | Success (seed 42) | Success (seed 43) |
|---|---|---|
| Single history, no budget (N = 1 + GRPO) | 48.20% | 47.60% |
| Single history, 30% budget (N = 1 + C³) | 47.00% | 46.40% |
| Joint, shared 30% budget (N = 3 + C³) | 51.40% | 50.80% |
Sensitivity to the budget. We evaluated models trained with different budgets at a larger deployment compaction threshold of 18,000 tokens, motivated by You don't need long context [2]. This checks how the calibration behaves when the agent can run longer between compactions.
| Initial budget-hit rate | 10% | 20% | 30% (default) | 50% |
|---|---|---|---|---|
| Success at 18,000 tokens | 57.0% | 60.0% | 59.5% | 50.5% |
The 10%, 20% and 30% targets give similar task success, which supports a range of moderate budget settings at this threshold.
[1] Yang et al. Batched Contextual Reinforcement. PMLR 306, 2026. [2] Belcak et al. You don't need long context. arXiv:2611.05306, 2026.
I appreciate the authors’ response and their answers to my questions. However, I still believe my initial overall rating reflects my assessment of the paper, and therefore I would like to keep it.
Response to Reviewer uyub (1/2)
We thank the reviewer for their time and efforts in reviewing our paper and their constructive feedbacks.
Memory allocation across checkpoints. We compared joint training (N = 3 + C³) with single-history training (N = 1 + C³) at checkpoints saved every 10 updates in the first training stage. Each validation prompt contains three histories. Let Li be the memory length in tokens for history i. The normalized memory-length gap is
Δmem=L1+L2+L3maxiLi−miniLi×100%
Uniform compression pressure, which shortens all three memories by the same factor, leaves Δmem unchanged. Changes in Δmem therefore reflect how the budget is split. At update 0, we compressed each history separately and used the resulting gaps to assign prompts to low-, medium- and high-dispersion groups. We tracked these same groups across checkpoints. The table shows the gap (%) every 20 updates.
Single-history training moves both extreme groups toward the middle. With the shared budget, the high-dispersion gap narrows at first and then reaches 21.36%, up from 17.73%, while the low-dispersion gap falls from 6.08% to 3.40%. Under joint training, memory lengths diverge for prompts that start with large gaps and become more uniform for prompts that start with small ones.
Task accuracy for long and short histories. We took the longest and the shortest history from each validation prompt and tracked downstream accuracy across checkpoints of the jointly trained compressor. Each cell is the number of correct outcomes out of 50.
Short-history accuracy stays between 34 and 38 throughout. Long-history accuracy rises from 32 at update 0 to 34 to 36 after update 50. This is consistent with shared-budget competition helping the compressor keep useful information from longer histories while maintaining accuracy on shorter ones.
Fixed per-history quotas. We also trained a baseline that divides the same total budget into equal quotas for the three memories in a joint prompt. How the quotas are enforced matters for training.
In 10 of the first 20 updates, all candidate outputs received the same reward, so GRPO had no signal to learn from. This made the fixed-quota baseline harder to train than our other baselines.