MemAgent
Free while signed in. Answers cite the passages they came from.
Introduces an RLādriven memory agent that enables transformer-based LLMs to handle documents up to 3.5 million tokens with near lossless performance, linear complexity, and no need for architectural modifications.
RL-shaped fixed-length memory: MemAgent reads documents in segments and maintains a fixed-size memory updated via an overwrite mechanism. This lets it process arbitrarily long inputs with O(N) inference cost while avoiding context window overflows.
Multi-conversation RL training (Multi-Conv DAPO): Unlike standard RL pipelines, MemAgent generates multiple independent memory-update conversations per input. It uses a modified GRPO objective to optimize all steps via final-answer reward signals.
Strong long-context extrapolation: Despite being trained on 32K-length documents with an 8K context window, MemAgent-14B achieves >76% accuracy even at 3.5M tokens, outperforming baselines like Qwen2.5 and DeepSeek, which degrade severely beyond 112K tokens.
Generalizes to diverse long-context tasks: On the RULER benchmark, it excels in multi-hop QA, variable tracking, frequent word extraction, and NIAH retrieval, even outperforming larger 32B baselines without RL. Its memory updates are interpretable and resilient to distractors.
Get next weekās papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack