MemRefine uses LLM factual judgments to iteratively compress agent memory to target budgets while preserving downstream task performance better than rule-based baselines.
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this issue, we propose StreamMeCo, an efficient Stream Agent Memory Compression framework. Specifically, based on the connectivity of the memory graph, StreamMeCo introduces edge-free minmax sampling for the isolated nodes and an edge-aware weight pruning for connected nodes, evicting the redundant memory nodes while maintaining the accuracy. In addition, we introduce a time-decay memory retrieval mechanism to further eliminate the performance degradation caused by memory compression. Extensive experiments on three challenging benchmark datasets (M3-Bench-robot, M3-Bench-web and Video-MME-Long) demonstrate that under 70% memory graph compression, StreamMeCo achieves a 1.87* speedup in memory retrieval while delivering an average accuracy improvement of 1.0%. Our code is available at https://github.com/Celina-love-sweet/StreamMeCo.
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
A hybrid graph-based training-free framework for LLM context compression matches strong baselines and shows larger gains on long-document benchmarks.
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
citing papers explorer
-
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
MemRefine uses LLM factual judgments to iteratively compress agent memory to target budgets while preserving downstream task performance better than rule-based baselines.
-
From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
A hybrid graph-based training-free framework for LLM context compression matches strong baselines and shows larger gains on long-document benchmarks.
-
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.