{"ID":2846641,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01950","arxiv_id":"2511.01950","title":"EchoLSTM: A Self-Reflective Recurrent Network for Stabilizing Long-Range Memory","abstract":"Standard Recurrent Neural Networks, including LSTMs, struggle to model long-range dependencies, particularly in sequences containing noisy or misleading information. We propose a new architectural principle, Output-Conditioned Gating, which enables a model to perform self-reflection by modulating its internal memory gates based on its own past inferences. This creates a stabilizing feedback loop that enhances memory retention. Our final model, the EchoLSTM, integrates this principle with an attention mechanism. We evaluate the EchoLSTM on a series of challenging benchmarks. On a custom-designed Distractor Signal Task, the EchoLSTM achieves 69.0% accuracy, decisively outperforming a standard LSTM baseline by 33 percentage points. Furthermore, on the standard ListOps benchmark, the EchoLSTM achieves performance competitive with a modern Transformer model, 69.8% vs. 71.8%, while being over 5 times more parameter-efficient. A final Trigger Sensitivity Test provides qualitative evidence that our model's self-reflective mechanism leads to a fundamentally more robust memory system.","short_abstract":"Standard Recurrent Neural Networks, including LSTMs, struggle to model long-range dependencies, particularly in sequences containing noisy or misleading information. We propose a new architectural principle, Output-Conditioned Gating, which enables a model to perform self-reflection by modulating its internal memory ga...","url_abs":"https://arxiv.org/abs/2511.01950","url_pdf":"https://arxiv.org/pdf/2511.01950v1","authors":"[\"Prasanth K K\",\"Shubham Sharma\"]","published":"2025-11-03T11:04:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}