S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
This paper proposes S3MEM, a structured scene-event memory framework for long-horizon interactive question answering. By writing trajectories into structured memory units, using anchor-sensitive retrieval, and exposing a compact token-budget-aware evidence interface, S3MEM significantly improves accuracy and efficiency in answering questions about early events. Experiments on multiple environments show that S3MEM achieves a better accuracy-efficiency frontier than existing methods.
Article intelligence
Key points
- S3MEM writes trajectories into structured memory units and retrieves evidence via anchor-sensitive retrieval with token-budget awareness.
- It outperforms Vanilla RAG across Crafter, Jericho, SciWorld, and ALFWorld, surpassing Graph-NoReader on three environments while using fewer evidence tokens.
- Under a frozen answer-time protocol, S3MEM provides a stronger accuracy-efficiency trade-off than generic memory interfaces.
Why it matters
This matters because s3MEM writes trajectories into structured memory units and retrieves evidence via anchor-sensitive retrieval with token-budget awareness.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.28831] S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
[Submitted on 10 Apr 2026]
Title:S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
View a PDF of the paper titled S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering, by Encheng Su and 10 other authors
View PDF HTML (experimental)
Abstract:Long-horizon interactive agents often accumulate large trajectory histories yet still fail to answer questions about earlier events reliably. We argue that the main bottleneck is not context length alone, but the trajectory-to-answer interface of long-term memory. When histories are stored as plain-text chunks and queried with standard retrieval-augmented generation (RAG), systems often retrieve locally relevant but chain-incomplete evidence, especially for spatial, temporal, repeated-event, and multi-hop state questions. We propose S3MEM, a structured scene-event episodic memory framework for long-horizon interactive question answering (QA). S3MEM writes trajectories into structured memory units, retrieves evidence through anchor-sensitive retrieval, and exposes a compact token-budget-aware evidence interface for answer-time inference. In this sense, S3MEM is a structured evidence harness that converts agent trajectories into query-aligned support. We evaluate S3MEM on two internal headline environments (Crafter, Jericho) and two out-of-family environments (SciWorld, ALFWorld). Under a shared frozen answer-time protocol, S3MEM consistently outperforms Vanilla RAG across all four environments, surpasses Graph-NoReader on Crafter, Jericho, and ALFWorld, and matches it on SciWorld while using dramatically fewer evidence tokens. Three adapted recent baselines -- A-MEM-inspired, MemoryOS-adapted, and LightMem-adapted -- improve over Vanilla RAG in several settings, but none matches S3MEM's overall accuracy-efficiency frontier. Overall, the evidence supports a bounded conclusion: under the current frozen answer-time protocol, structured writing and anchor-sensitive evidence routing provide a stronger accuracy-efficiency frontier for long-horizon interactive QA than more generic memory interfaces.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.28831 [cs.CL]
(or arXiv:2605.28831v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.28831
arXiv-issued DOI via DataCite
Submission history
From: Encheng Su [view email] [v1] Fri, 10 Apr 2026 07:49:10 UTC (4,279 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering, by Encheng Su and 10 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)