MemDuet: Learning Dual-Process Memory for Long-Context Reasoning

arXiv:2610.19928v1 Announce Type: new Abstract: Reasoning over infinitely long documents is becoming a reality with recurrent memory agents. However, increasing context length exacerbates the trade-off between reasoning performance and inference efficiency. Inspired by Kahneman's account of fast and slow thinking, we propose MemDuet, a dual-process memory framework that learns to coordinate a small language model for fast, parallel evidence selection from raw context chunks (System 1) with a large language model for memory-update verification and memory updates in document order (System 2). We train MemDuet in three stages: supervised fine-tuning of System 1 for evidence selection, Group Relative Policy Optimization (GRPO) of System 2 for verification and memory rewriting, and joint optimization of both policies to coordinate selection and updating for long-context reasoning. Experiments on diverse long-context reasoning benchmarks (RULER-HQA, LongBench v2, and 2WikiMultiHopQA) demonstrate a favorable accuracy-efficiency trade-off as context length grows. Averaged across evaluation settings on the three datasets, MemDuet achieves an end-to-end inference speedup of 9.74x and an output-token reduction of 73.91% relative to RL-MemAgent.

Related

• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
• Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
• EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
• MemReader: From Passive to Active Extraction for Long-Term Agent Memory

Source: arXiv cs.CL | 2026-10-15