- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes State-Adaptive Memory (SAM), an external memory framework for LLM agents performing long tasks. Its central idea is to keep past interactions recoverable without carrying the entire history in the agent’s context. SAM divides interaction histories into pages, stores the original pages externally, and retains compact summaries called memory cues in the active context. When earlier information becomes relevant, the agent selects cues and specifies what it needs to recall. A separate memory model then reads the corresponding pages and returns information tailored to that request.
The authors train a Qwen3.5-9B memory model while keeping the main agent frozen. Training combines supervised learning from successful expert trajectories with Oracle-Anchored Tree GRPO (OAT-GRPO). This reinforcement-learning method branches at memory calls to compare alternative recall outputs, using both downstream task success and assessments against reference outputs from stronger models.
Experiments cover BrowseComp, BrowseComp-ZH, WideSearch, and HLE with two agent backbones. SAM improves the average benchmark score from 49.4 to 57.0 for GLM-4.7 and from 44.5 to 48.8 for Qwen3.5-35B-A3B, outperforming the tested truncation and summarization baselines. Ablations support the usefulness of both training stages and intent-conditioned recall. The main contribution is a reusable memory module that combines compact context with on-demand access to detailed history, allowing memory access to change as the agent’s task progresses.
Critical strengths
-
SAM offers a practical way to preserve access to detailed history while keeping the agent’s active context compact. Its memory cues point to stored trajectory pages, allowing the agent to recover information according to its current needs. The recall ablations support this design: on BrowseComp, full SAM achieves 42.2, compared with 39.0 for summary-only memory and 38.0 for raw-page readout. This is meaningful evidence that selective reconstruction can help beyond simply retaining or summarizing history.
-
The same trained memory module improves results across two frozen agent backbones and four benchmarks. SAM outperforms the included context-management heuristics in all eight backbone–benchmark combinations. Although this does not establish superiority over the closest learned memory systems, the consistency is encouraging. It supports the practical value of a reusable memory component that can improve different agents without retraining their reasoning models.
Critical weaknesses
-
The contribution over closely related memory and training methods is not sufficiently established. GAM[1] already combines lightweight memory with a complete page store for request-conditioned retrieval, while Mem-T[2] uses memory-operation trees to derive intermediate training signals from downstream outcomes. Neither is discussed. The controlled comparisons are primarily against truncation and summarization heuristics, leaving unclear what SAM’s architecture and OAT-GRPO add beyond existing approaches.
-
The experiments do not adequately isolate the proposed mechanisms, and a configuration mismatch makes the gains harder to assess. Removing OAT-GRPO shows that the complete RL stage helps, but does not distinguish the effects of tree-based credit assignment, task rewards, and committee-based rewards. There is also no untuned memory model using the identical SAM architecture. Together, these gaps leave uncertainty about which components produce the gains and how consistently those gains are measured.
[1] Yan, B. Y., et al. "General agentic memory via deep research." arXiv preprint arXiv:2511.18423 (2025).
[2] Yue, Yanwei, et al. "Mem-t: Densifying rewards for long-horizon memory agents." arXiv preprint arXiv:2601.23014 (2026).
Questions for authors
-
What distinguishes SAM’s cue–page architecture from GAM’s lightweight memory and complete page store, and OAT-GRPO from Mem-T’s memory-operation tree training? Which differences do you consider essential to the reported improvements?
-
Do you have results separating tree-based credit assignment from the committee and task-outcome rewards, ideally with matched training budgets? An untuned 9B model using the same SAM architecture would also help establish how much improvement comes from the architecture versus training.
8 comments
[Part 2/4] Response to Reviewer gGG4
2. Comparison with Mem-T: the focus is the current task's working context, rather than the full lifecycle of a memory store.
Mem-T organizes working, factual, experiential, and raw memory into a hierarchical system and learns operations such as formation, updating, and retrieval. It includes working memory, so the distinction is not whether working memory is present. Rather, SAM focuses on history management and recall reconstruction within a single task, while Mem-T also addresses broader memory-store maintenance.
| Dimension | GAM | Mem-T | SAM |
|---|---|---|---|
| Managed content | Continuously growing history and its page store | Working, factual, experiential, and raw memory | Reasoning and interaction history in the current session |
| Main access operations | Iterative search, synthesis, and reflection around a request | Retrieval from different memory modules, combined with memory formation and updates | The main agent specifies intent and pages; the external model reconstructs the needed content |
| Use goal considered here | Generate context for client requests | Maintain and use a hierarchical memory store | Reuse earlier evidence from the current task for later decisions |
In training, Mem-T's tree nodes represent memory retrieval operations, and retrieval utility is traced back to memory construction. SAM branches at the same recall request to compare different readouts under the same main-agent state. Mem-T uses intra-tree and inter-tree advantage estimation, while SAM forms comparison groups from sibling candidates sharing a parent state. Their auxiliary feedback also focuses on retrieved evidence and recall recoverability based on raw pages, respectively.
The reason for this design is that we want to train the memory content returned to the main agent at this particular call. Comparing candidates under the same need and page conditions reduces the effect of differences in task state on the training signal. The tree structure serves the memory mechanism here, and its separate role is tested in the Optimization ablations below.
3. Read ablations directly test the value of intent-conditioned reconstruction.
You have already noted the difference between Raw-content and full SAM. Here, we further link each baseline to the specific mechanism it tests: Figure 2 fixes the write side and page store and compares how the same history is used.
| Read method | Qwen BrowseComp | Factor tested |
|---|---|---|
| Summary-only | 39.0% | Uses only the summary formed at write time |
| Recency | 37.0% | Accesses pages by recency, without guidance from current needs |
| Raw-content | 38.0% | Provides raw pages without intent-conditioned reconstruction |
| SAM | 42.2% | Reconstructs relevant information from raw pages based on current intent |
SAM improves over Raw-content by 4.2 percentage points and over Summary-only by 3.2 percentage points. The former shows that even after raw text is saved and made available again, how this information is processed still affects task outcomes. The latter shows that write-time summaries cannot fully replace recovering details for new needs at read time. Together, the two comparisons support preserving recoverable history and reorganizing information when needed.
Adapting GAM-style retrieval, synthesis, and reflection to the same online task interface, with the same Qwen main backbone, tools, and system-wide total token cap, gives 41.0% on BrowseComp, compared with 42.2% for full SAM. This comparison shows that SAM's complete access and training scheme provides additional gains under the current task protocol. The difference includes the joint effects of workflow and training. The same-architecture comparison below further separates the contribution of training, avoiding attributing both effects entirely to the page interface.
[Part 3/4] Response to Reviewer gGG4
W2 / Q2: Architecture
You suggested that an untuned 9B model under the same architecture would help separate the contributions of architecture and training. We address this by keeping storage, the call interface, and the main agent unchanged, and varying only the memory model's training status. This directly tests whether gains come from connecting this interface or also depend on the memory model learning to use it more effectively.
| Configuration | GLM average over four tasks |
|---|---|
| No context management | 49.4 |
| Same SAM architecture, untuned 9B | 54.3 |
| Same SAM architecture, SFT-only | 55.6 |
| Same SAM architecture, w/o SFT, RL-only | 55.9 |
| Same SAM architecture, SFT + OAT-GRPO | 57.0 |
1. Connecting an untuned module already helps, but specialized training adds further gains.
The untuned 9B model reaches 54.3 when connected to SAM, improving by 4.9 points over no context management. This shows the practical value of the full interface for history consolidation, storage, and on-demand access. With exactly the same interface, SFT raises the score to 55.6, and full training further raises it to 57.0. The full model's 2.7-point improvement over the untuned model therefore cannot be explained solely by adding another model or keeping raw logs.
This also explains why SAM studies both the architecture and external-module training: the interface makes history usable, while training improves how much the returned content helps the current task. Both contribute to the final result.
2. The paper's w/o SFT variant and a fully untuned model are different controls.
The w/o SFT score of 55.9 still includes RL, so it tests whether reinforcement learning needs supervised initialization. The newly added untuned 9B model receives neither SAM SFT nor RL, and tests what the interface can achieve without specialized training. Presenting them side by side keeps gains from training from being counted as gains from the untrained architecture.
The main agent's parameters remain frozen throughout. RL uses GPT-5.4 for subsequent reasoning, and gradients update only the memory model. After training, the same module is connected to GLM and Qwen. These differences therefore reflect changes in external memory-processing capabilities.
W2 / Q2: Optimization
Your concern is how much tree-local credit assignment, task outcomes, and committee feedback each contribute, rather than just whether removing all RL lowers the score. We cross the credit-assignment methods with reward components under the same architecture, SFT initialization, and training tasks, matching rollout token budgets to test local comparison and auxiliary feedback separately. The budget includes subsequent execution by the frozen reasoner. Mixed-reward groups use the same committee configuration and scoring method.
| Method | Reward components | GLM average over four tasks |
|---|---|---|
| SFT-only | — | 55.6 |
| Standard trajectory-level GRPO | Task outcome only | 55.9 |
| Standard trajectory-level GRPO | Task outcome + recoverability | 56.2 |
| Tree-local credit assignment | Task outcome only | 56.4 |
| Tree-local credit assignment | Recoverability only | 55.8 |
| Full OAT-GRPO | Task outcome + recoverability | 57.0 |
1. Local credit assignment links task feedback to specific recall actions.
Final failure of a long trajectory does not mean that every recall in it had no value. For example, the memory model may have recovered key time information, but the main agent may make an incorrect judgment later. If all intermediate actions share one final outcome, it is difficult to distinguish which recalls are worth retaining.
OAT-GRPO generates different readouts with the same intent, pages, and main-agent state, then lets the frozen reasoner continue execution. The comparison thus starts from the same point, and the training signal is more directly tied to the effect of the current readout. With task outcome rewards alone, local credit assignment improves over trajectory-level GRPO by 0.5 points. When both use mixed rewards, it still improves by 0.8 points. These gains therefore remain under the same reward conditions, supporting comparisons at the level of memory actions themselves.
[Part 1/4] Response to Reviewer gGG4
Thank you for recognizing the practical value of SAM in preserving detailed history while keeping the active context compact, and for noting the evidence from read ablations and consistent gains on two frozen backbones. To address your concerns about related work, the contributions of the mechanisms, and configuration consistency, we first clarify the scope of this paper, then explain the roles of the architecture and training separately.
First, SAM studies working memory within a single long-horizon task, which can also be understood more directly as context management. Memory in this paper does not span sessions: pages and cues support the ongoing execution of the current task and are not passed to other tasks as a cross-session memory store. We use the term Memory following the functional taxonomy in Memory in the Age of AI Agents. In §4.3, that survey defines working memory as mechanisms for actively managing and manipulating context within a single episode, and includes state maintenance across multiple interaction turns in this category. Thus, SAM's memory focuses on preserving, selecting, and reconstructing historical information within the current task.
This positioning also defines the main problem of the paper: how a frozen main agent can continue using earlier information as search, tool feedback, and intermediate judgments accumulate, when the importance of that information only becomes clear later. Connecting the trained memory module to different main agents means reusing its memory-processing capability; the actual history stored for each task remains separate.
W1 / Q1: Positioning
You noted that GAM already has lightweight memory and a complete page store, and that Mem-T already uses memory-operation trees to assign intermediate feedback, so we need to explain what SAM adds. Our distinction is to embed memory processing in the execution of a single task and train an external module to reconstruct the historical evidence currently needed into content usable for the next decision. Below, we explain the relationship to each work and which experiments directly test this design.
1. Comparison with GAM: both preserve recoverable history, but the access workflows and evaluation goals differ.
GAM uses a Memorizer to maintain lightweight memory and a page store, and a Researcher to iteratively plan, search, synthesize, and reflect around a request. It also discusses a framework that freezes the client and optimizes the memory module. Thus, SAM's differences need to be specified in terms of online history processing and recall training; they cannot be summarized solely as a structure of summaries plus raw text.
In SAM, raw pages come from the task the main agent is currently executing. Once the context reaches the threshold, the system consolidates history and leaves visible cues. The main agent then selects pages and issues a recall intent based on its current judgment. The memory model reconstructs the needed information directly from these pages, and the main agent continues searching or reasoning after receiving it. For example, the same history may help identify candidate entities early on and later be needed to check a time constraint. Information needs change with the decision state, and an early summary may not cover later needs in advance.
Thus, SAM's core test is whether reconstruction actually improves later execution when the same history is reused in different states. GAM's request-conditioned synthesis overlaps with this goal. SAM further trains recall outputs within an ongoing task and evaluates their utility through actual task outcomes.