- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
FlowState is a training-free framework that treats an LLM agent's execution state as its long-term memory. The runtime keeps a Persistent State Repository of semantically typed state nodes (user preferences, environment knowledge and attributes, agent judgements, artifacts), their typed relations, and references to raw tool observations, but only places a compact Historical State Index of identifiers and one-line summaries in the model context. At each ReAct step the frozen policy jointly emits a state delta, a historical access request, and an action: Incremental State Update (ISU) adds, updates, or removes current-request nodes without regenerating the whole state, while Progressive State Access (PSA) expands selected historical nodes and, by following their disclosed relations, drills down to supporting evidence on demand. Against a Full Context baseline with the same DeepSeek-V4-Flash model, FlowState raises average success rate on MemoryArena by 4.55 points and average pass rate on τ3-Bench by 13.95 points while cutting total tokens by 43.2% and 40.6%, beats ReasoningBank, BM25, Mem0, ZipAct, and ZipAct+BM25 on most MemoryArena metrics, and shows similar gains with GPT-5.6-terra and Qwen3.5-397B-A17B. Ablations indicate ISU is needed for task success and PSA for token efficiency, and per-subtask analysis shows FlowState retains accuracy at later subtask depths where baselines collapse, though absolute success rates on Shopping and Travel remain near zero for all methods and no variance across runs is reported.
Critical strengths
- Clear and well-motivated design principle. The paper identifies a real gap between state-tracking methods that compress away details and memory systems that retrieve blindly. Its answer, keep everything persistently but expose only an index and let the agent expand on demand, is simple and addresses the stated failure modes directly. The hotel example in Figure 1 makes the problem concrete.
- Gains in both accuracy and token cost at once. Most methods trade one for the other. FlowState improves over Full Context on eight of nine MemoryArena performance metrics and both τ3-Bench domains while cutting tokens by roughly 40%. The comparison is fair in the sense that both use the same frozen model and the same tasks, tools, and scoring.
- Ablations support both components. Replacing ISU with rule-built boundary nodes drops success rate to zero in both tested environments, and exposing all history instead of PSA costs more tokens and hurts Travel. This is reasonable evidence that the two mechanisms play distinct roles.
Critical weaknesses
- Prompt confound between FlowState and baselines. FlowState runs with a long, carefully engineered instruction block and a structured four-field output protocol. The baselines use the benchmarks' released prompts. Part of the gain may come from better instructions and forced structured reasoning rather than from the memory architecture. A prompt-matched control, for example Full Context with the same ISU instructions but no persistence, is missing.
- Baselines are evaluated on one model only. The cross-model claim compares FlowState to Full Context on three models. All memory and state-tracking baselines are DeepSeek-V4-Flash only, so there is no evidence FlowState beats the field on GPT-5.6-terra or Qwen.
- Ablations are replacements, not removals, and do not isolate design choices. The no-ISU variant builds a single node from the final response per query, which is a deliberately weak alternative, so the SR-to-zero result mostly shows that one summary node is insufficient. The no-PSA variant exposes all history and still gets the best Shopping PS. Nothing tests the five-type taxonomy, the relation types, raw observation references, or the one-step disclosure delay.
- Near-zero absolute success on the two flagship environments. Shopping SR is 5.33% and Travel SR is 0.74% for the best method. The ranking rests on progress scores whose definitions differ across environments, and the paper does not discuss why all methods fail so badly.
Questions for authors
- Are all reported results single runs? Can you provide results over at least three seeds with standard deviations, especially for Travel SR (one vs two tasks out of 270), Physics SR (one task out of 20), and Math SR (three tasks out of 40)?
- Could you add a prompt-matched control: Full Context with the same instruction block and four-field output protocol as FlowState, but without the repository, index, or PSA? This would separate the effect of the memory architecture from the effect of the engineered prompt.
8 comments
Response to fknD (2/4): Controlled ablations of individual design choices
W3 (Part 1): Individual contributions of the design choices
Ablations are replacements, not removals, and do not isolate design choices. The no-ISU variant builds a single node from the final response per query, which is a deliberately weak alternative, so the SR-to-zero result mostly shows that one summary node is insufficient. The no-PSA variant exposes all history and still gets the best Shopping PS. Nothing tests the five-type taxonomy, the relation types, raw observation references, or the one-step disclosure delay.
Thank you for this suggestion. We acknowledge that the original ablations primarily compared components and were insufficient to isolate the contribution of each design choice. To address this concern, we added five controlled variants on Math and Physics. Each starts from the full FlowState framework and changes only one mechanism:
- No evidence access: The agent can still read historical states but cannot revisit the raw tool outputs supporting them. State content, relations, and current observations are retained.
- No relation navigation: When a historical state is disclosed, links to its related states are hidden. The agent can still select and disclose historical states through the Historical State Index and independently access raw evidence.
- No node types: We collapse the five state types into a single generic type, keeping all other design choices unchanged.
- No relation types: We replace the relation labels between states with a single generic type, keeping all other design choices unchanged.
- Full-state rewriting: We keep the update timing unchanged but require the agent to regenerate all modifiable states for the current request, rather than returning only additions, updates, and removals.
SR and PS are reported as percentages, and token consumption is reported in millions. Results are presented as mean ± standard deviation.
| Variant | Math SR | Math PS | Math tokens (M) | Physics SR | Physics PS | Physics tokens (M) |
|---|---|---|---|---|---|---|
| Full FlowState | 42.50 ± 5.00 | 55.77 ± 0.25 | 12.95 ± 1.73 | 61.67 ± 2.89 | 74.88 ± 2.10 | 1.98 ± 0.18 |
| No evidence access | 39.17 ± 3.82 | 53.68 ± 1.70 | 14.01 ± 0.43 | 53.33 ± 12.58 | 69.38 ± 3.85 | 2.10 ± 0.04 |
| No relation navigation | 40.83 ± 1.44 | 53.44 ± 1.38 | 13.65 ± 0.17 | 55.00 ± 10.00 | 71.06 ± 5.40 | 2.05 ± 0.03 |
| No node types | 41.67 ± 1.44 | 53.97 ± 2.00 | 13.70 ± 0.05 | 53.33 ± 2.89 | 68.87 ± 3.66 | 2.03 ± 0.07 |
| No relation types | 40.83 ± 1.44 | 55.93 ± 0.67 | 13.87 ± 0.28 | 50.00 ± 5.00 | 69.42 ± 2.17 | 2.13 ± 0.06 |
| Full-state rewriting | 31.67 ± 1.44 | 54.58 ± 1.54 | 13.72 ± 0.19 | 58.33 ± 2.89 | 72.80 ± 2.68 | 1.91 ± 0.13 |
As shown above, all five variants have lower mean SR than full FlowState in both domains. With access to historical states retained, the first four comparisons support the contributions of node types, relation semantics, relation navigation, and access to raw evidence. Full-state rewriting reduces mean SR despite preserving the update timing and the scope of modifiable states, further supporting the value of incremental maintenance. These experiments connect the overall gains to specific design choices, going beyond component-level replacements.
Response to fknD (3/4): Disclosure timing and benchmark difficulty
W3 (Part 2): Historical access and disclosure timing
Nothing tests the five-type taxonomy, the relation types, raw observation references, or the one-step disclosure delay.
Regarding the one-step disclosure delay, we clarify that historical information becomes visible in the next model invocation after an access request, but the agent can request retrieval alone and wait for the information before acting. When the current action does not depend on the information to be retrieved, the agent can also request historical information and execute an action in the same step.
To assess whether mandatory waiting is beneficial, we compare two scheduling settings:
- Joint scheduling: The agent chooses whether to retrieve historical information alone or to request retrieval and execute an action in the same step.
- Sequential scheduling: Every retrieval request pauses environment actions until the historical information is returned, after which the agent makes its next decision.
In both settings, historical information is disclosed in the next model invocation. The only difference is whether retrieval and environment actions must be executed sequentially.
SR and PS are reported as percentages, and token consumption is reported in millions. Results are presented as mean ± standard deviation.
| Scheduling | Math SR | Math PS | Math tokens (M) | Physics SR | Physics PS | Physics tokens (M) |
|---|---|---|---|---|---|---|
| Joint scheduling | 42.50 ± 5.00 | 55.77 ± 0.25 | 12.95 ± 1.73 | 61.67 ± 2.89 | 74.88 ± 2.10 | 1.98 ± 0.18 |
| Sequential scheduling | 40.00 ± 2.50 | 55.93 ± 0.19 | 13.85 ± 0.31 | 60.00 ± 8.66 | 74.12 ± 3.33 | 2.05 ± 0.04 |
The two settings yield similar mean task performance, while joint scheduling uses slightly fewer tokens. In qualitative trajectory analysis, we observe that the agent retrieves first and acts afterward when it needs historical information to decide on an action. When the available information already supports the current action, it can act and request retrieval in the same step. These results support allowing the agent to decide when to wait, without requiring sequential execution for every historical access request.
W4: Absolute success rates and the interpretation of progress metrics
Near-zero absolute success on the two flagship environments. Shopping SR is 5.33% and Travel SR is 0.74% for the best method. The ranking rests on progress scores whose definitions differ across environments, and the paper does not discuss why all methods fail so badly.
Thank you for highlighting this issue. The key difficulty in Shopping and Travel is integrating local decisions across sessions into a complete solution that satisfies all interdependent constraints. In Shopping, subsequent purchases must satisfy compatibility and preference constraints associated with earlier items. In Travel, each subtask contains 30 itinerary entries and involves dependencies across travelers and activities. Correctly completing some purchases or satisfying some itinerary constraints therefore does not guarantee that the final product bundle or overall itinerary passes evaluation. The original MemoryArena paper reports the same phenomenon: all methods in its Table 3 have zero Travel SR, and the listed external-memory and RAG methods also have zero Shopping SR [1].
Methods are compared under consistent evaluation rules within each environment. We fully adopt the evaluation rules and SR, PS, and sPS definitions of the MemoryArena implementation. All methods use the same tasks and completion criteria within each environment, so each comparison in the main results table rests on a consistent evaluation basis.
FlowState's results illustrate the gap between task progress and complete success. Higher progress scores reflect gains in completing individual subtasks or satisfying constraints, whereas low SR indicates that producing globally consistent product bundles and itineraries remains a major challenge. We therefore report both overall success rates and progress metrics to capture performance at the levels of complete task success and fine-grained progress.
[1] Zexue He et al. MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks. 2026.
Response to fknD (1/4): Prompt-matched controls and cross-model baselines
Thank you for your careful review and for recognizing FlowState's design motivation, performance and cost benefits, and the roles of its two core mechanisms. We appreciate your suggestions on prompt-matched controls, cross-model comparisons, and ablations. We have carefully considered these concerns and provide additional results and explanations below.
W1 and Q2: Separating prompt effects from the contribution of the memory architecture
Thank you for this suggestion. To separate the contributions of the prompt and the memory architecture, we added a Full Context baseline on Math and Physics with a prompt matched to FlowState: Prompt-matched Full Context.
This baseline uses FlowState's system prompt and four-field output protocol from Appendix B.3 and retains the full conversation history. It records
state_deltaandstate_focusonly as ordinary messages, without executing the corresponding state operations or implementing the Persistent State Repository, Historical State Index, or PSA mechanism.All methods in this comparison use DeepSeek-V4-Flash. The table reports mean ± standard deviation, with SR and PS expressed as percentages and token consumption in millions.
FlowState retains higher task performance and lower token consumption after matching the prompt and four-field output protocol. Compared with Prompt-matched Full Context, FlowState improves mean SR by 10.83 and 11.67 percentage points and PS by 3.40 and 10.83 percentage points on Math and Physics, respectively, while reducing token consumption by 72.1% and 66.9%. This comparison supports the contribution of the memory architecture beyond the prompt and structured output: by continuously maintaining reusable states and accessing historical information on demand, FlowState improves both task performance and context efficiency.
W2: Comparing memory and state-tracking baselines across models
Thank you for this suggestion. To test whether FlowState's advantages over different types of baselines extend beyond a single model, we added a full baseline comparison on Math and Physics using Qwen3.5-397B-A17B, covering Full Context, ReasoningBank, BM25, Mem0, ZipAct, and ZipAct+BM25. The table reports mean ± standard deviation, with SR and PS expressed as percentages and token consumption in millions.
Qwen3.5-397B-A17B
As shown above, FlowState achieves the highest mean SR and PS in both domains with Qwen3.5-397B-A17B, while using fewer tokens than Full Context. Together with the original DeepSeek-V4-Flash experiments, these results show that FlowState's performance advantages over multiple memory and state-tracking baselines extend to another model, providing further empirical evidence of its applicability across models.