From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multimodal large language models struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. |
| Approach: | They propose a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory that structures memory hierarchically into a *Sensory Buffer*, *Episodic Stream*, and *Symbolic Schema*. |
| Outcome: | The proposed architecture achieves state-of-the-art on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization. |
Similar Papers
Reducing Peak Memory Usage for Modern Multimodal Large Language Model Pipelines (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reduce memory usage of multimodal large language models rely on storing large numbers of vision tokens in the key–value cache . however, such compression is typically only applied after all inputs are processed, resulting in high peak memory usage during the prefill stage. |
| Approach: | They propose a sequential input-compression mechanism that enforces a fixed memory budget by performing structure-aware key–value cache compression during the prefill stage. |
| Outcome: | The proposed approach reduces peak memory usage while maintaining generative performance with only minimal degradation, enabling more practical and memory-efficient multimodal inference. |
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects (2026.findings-acl)
Copied to clipboard
Jun Zhang, Yicheng Ji, Feiyang Ren, Yihang Li, Bowen Zeng, Zonghao Chen, Ke Chen, Lidan Shou, Gang Chen, Huan Li
| Challenge: | Large Vision-Language Models are hindered by a systemic efficiency barrier known as visual token dominance. |
| Approach: | They propose a systematic taxonomy of efficiency techniques structured around the inference lifecycle . they examine visual encoding, prefilling, and decoding to understand bottlenecks . |
| Outcome: | The proposed techniques reveal how upstream decisions dictate downstream bottlenecks . the proposed techniques include hybrid compression and modality-aware decoding . |
VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing systems that use long-context modeling incur computational and memory overhead. |
| Approach: | They propose a visual memory framework that pre-rendered text into structured images and stored as visual notes for agentic systems. |
| Outcome: | The proposed system reduces token consumption while preserving effective long-term memory recall. |
An Efficient Context-Dependent Memory Framework for LLM-Centric Agents (2025.naacl-industry)
Copied to clipboard
| Challenge: | a recent study has demonstrated that context-dependent memory encoding can help to retrieve key memory cues essential for problem-solving. |
| Approach: | They propose an efficient architecture miming human memory processes through multistage encoding, context-aware storage, and retrieval strategies for LLM-centric agents. |
| Outcome: | The proposed architecture surpasses state-of-the-art online LLM-centric approaches on two interactive decision-making benchmarks in the navigation and manipulation domain. |
MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods rely on unstructured retrieval or coarse abstractions, which lead to temporal conflicts, brittle reasoning, and limited traceability. |
| Approach: | They propose a unified memory framework that consolidates long-term agent experiences into three interconnected components that combine structured knowledge and evidence to construct compact yet information-dense contexts for reasoning. |
| Outcome: | The proposed framework significantly improves multi-hop and temporal reasoning accuracy while reducing input context length by over 95% compared to long-context baselines. |
Cognitive Scaffold: From Fluid Context to Crystallized Memory for Long-Horizon DeepResearch Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Scaling LLM-based agents to long-horizon deep research is constrained by context-noise trade-off . solving a single query may require hundreds of interactions with noisy environments . |
| Approach: | They propose a factorized memory architecture that decouples the cognitive state into a Fluid Working Context for immediate reasoning and a persistent Knowledge Graph for long-term retention. |
| Outcome: | The Cognitive Scaffold outperforms baselines on Xbench-DeepSearch, BrowseComp-ZH, and GAIA . it achieves 74.7% Avg@3 and 87.0% Pass@3 on xbench, browseComp, and 88.3% Pass@3. |
MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection (2026.acl-industry)
Copied to clipboard
| Challenge: | Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. |
| Approach: | They propose a memory-augmented multi-modal LLM agent that leverages episodic memories to guide decisions on recurring and novel threats. |
| Outcome: | The proposed agent outperforms state-of-the-art phishing detection tools on two public datasets and improves recall by 20%. |
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated enhanced reasoning capabilities, evolving from simple Chain-of-Thought (CoT) prompting to advanced, product-oriented solutions like OpenAI o1 . |
| Approach: | They propose a strategy that shifts image input to critical reasoning stages and compresses redundant visual tokens via dynamic pruning. |
| Outcome: | The proposed model achieves state-of-the-art on five mathematical reasoning benchmarks (+3.4% vs previous sota) and demonstrates iterative reasoning capabilities for complex multi-step tasks. |
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing memory systems represent conversation history as unstructured embedding vectors, retrieving information through semantic similarity. |
| Approach: | They propose a bio-inspired memory architecture that models memory as a dynamic graph with Hebbian learning dynamics. |
| Outcome: | The proposed architecture leverages both semantic similarity and learned associations . it can be used to build a bio-inspired memory graph with Hebbian learning dynamics . |
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding (2025.findings-naacl)
Copied to clipboard
Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, Jiang Gui
| Challenge: | Multimodal foundation models have demonstrated significant success in tasks such as visual captioning, question answering, and image-text retrieval. |
| Approach: | They propose a specialized cognitive module, temporal working memory, which selectively retains task-relevant information across temporal dimensions. |
| Outcome: | The module retains task-relevant information across temporal dimensions, ensuring that critical details are preserved throughout the processing of video and audio content. |