研究人员正在开发新方法，以改进大型语言模型处理长对话历史和复杂文档的方式。几篇论文介绍了旨在克服有限上下文窗口限制的新型架构和基准测试。这些方法侧重于高效的记忆检索、摘要和跨对话及外部文档的联合推理，以增强模型在扩展交互中的性能。 AI
影响 这些进展旨在显著提高大语言模型在扩展对话和复杂文档分析中的能力，从而实现更复杂的人工智能应用。
排序理由 多篇学术论文介绍了处理大语言模型长上下文和记忆的新方法和基准测试。
AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →
arXiv:2606.05182v1 Announce Type: new Abstract: Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered Archival aNd Temporal Episodic Retrieval Network), a lightweight memory layer th…
arXiv:2512.20111v2 Announce Type: replace Abstract: As the time horizons of sequential decision-making tasks grow, keeping full interaction histories in model context becomes increasingly costly. Recent work reduces context lengths by instead conditioning decision-making agents o…
arXiv:2606.04442v1 Announce Type: cross Abstract: AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehension within long documents. Yet no existing benchmark evaluates both simultaneo…
arXiv:2606.04591v1 Announce Type: new Abstract: With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. Users often need to retrieve coherent dialogue fragments related to specific topi…
arXiv:2606.04194v1 Announce Type: cross Abstract: Retrieving the few past turns that answer a new query across long multi-session histories is the retrieval bottleneck behind long-term conversational memory (LoCoMo, LongMemEval). Recent concurrent work, Nano-Memory, shows that sc…
With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. Users often need to retrieve coherent dialogue fragments related to specific topics, rather than isolated utterances. We propose …
AI systems increasingly need to combine two demanding capabilities: navigating multi-session conversation history and performing deep reading comprehension within long documents. Yet no existing benchmark evaluates both simultaneously. We introduce MemoryDocDataSet, a synthetic b…
Retrieving the few past turns that answer a new query across long multi-session histories is the retrieval bottleneck behind long-term conversational memory (LoCoMo, LongMemEval). Recent concurrent work, Nano-Memory, shows that scoring a session by the maximum query-turn similari…
arXiv:2606.01223v1 Announce Type: cross Abstract: Despite substantial progress in long-context modeling, existing benchmarks remain confined to factual memory for explicit recall, failing to measure the reflective memory required to synthesize fragmented, multimodal cues into hig…