LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding

ArXi:2601.11913v2 Announce Type: replace-cross Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often encounter additional computational costs or constrained expanded context length. While multi-agent-based frameworks can mitigate these limitations, they remain susceptible to the accumulation of errors and the propagation of hallucinations.