一种新设计的长文本智能体模型 PARSER
This is a brilliant paper. It's of the cleanest long-context agent designs I have seen in the past ...
朋友，我给你推荐这篇论文，它提出了一种叫 PARSER 的长文本智能体设计，特别适合处理超长文档，比传统方法快很多，还更准确。
这篇论文提出了一种名为 PARSER 的长文本智能体设计。它通过将文档分块并行处理，解决了传统方法中推理深度与文档遍历的耦合问题。在 896K 令牌的多跳问答任务上，4B 版本的 PARSER 相比最强基线提升了 5.7 个百分点。9B 版本在性能上超过了 DeepSeek-V4-Pro。该模型通过控制实验验证了其在证据位置、顺序和距离变化下的鲁棒性，并显著降低了推理延迟。
This is a brilliant paper. It's of the cleanest long-context agent designs I have seen in the past ...
This is a brilliant paper. It's of the cleanest long-context agent designs I have seen in the past couple of months. Sequential memory agents read chunks one after another while maintaining a compact memory state. This behavior ties reasoning depth to document traversal and makes accuracy sensitive to where the evidence sits. It also makes latency grow linearly with document length. PARSER decouples the two. A bank of lightweight subagents, each bound to a single chunk, reads the whole document in parallel. A lead agent reasons through iterative scatter-gather rounds, broadcasting a query to all subagents, aggregating the returned evidence, and forming a deeper follow-up query conditioned on what it has found. All the learnable behavior is build into the lead agent, which is trained with RL. The subagents stay frozen off-the-shelf models. On multi-hop QA from 7K to 896K tokens, a 4B PARSER beats the strongest sequential memory baseline by 5.7 points on average and 12.0 points at 896K. At 9B it passes DeepSeek-V4-Pro by 6.3 points. Controlled experiments show it holds up under perturbations to evidence position, order and distance, which cause large accuracy swings in sequential methods, while cutting inference latency by up to 11x. Paper: academy.dair.ai/papers/parser-… 💬 9 🔄 15 ❤️ 69 👀 6246 📊 33 ⚡