PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
PARSER uses parallel reader subagents and an RL-trained lead agent for long-context QA, beating baselines and cutting latency up to 11x.
The PARSER paper decouples reading from reasoning: frozen subagents each read one document chunk in parallel while an RL-optimized lead agent iteratively broadcasts queries and aggregates evidence in scatter-gather rounds. On multi-hop QA with 7K to 896K token contexts, a 4B-backbone PARSER beats the strongest sequential memory baseline by 5.7 points on average and 12.0 points at 896K tokens, and a 9B version surpasses DeepSeek-V4-Pro by 6.3 points. Controlled experiments show robustness to evidence position, order, and distance perturbations, with inference latency reduced by up to 11x.
- Subagents read 7K-896K token documents in parallel while a lead agent performs iterative scatter-gather reasoning.
- 4B backbone beats the strongest sequential memory baseline by 12.0 points at 896K tokens.
- 9B version surpasses DeepSeek-V4-Pro by 6.3 points on multi-hop QA.
- Reduces inference latency by up to 11x versus sequential memory agents.
- Vendors
- DeepSeek
- Products
- PARSER
- AI models
- DeepSeek-V4-Pro
From the original article
1 min read at huggingface.coSequential memory agents process long documents by reading chunks one after another while maintaining a compact memory state, coupling document traversal to reasoning depth. This coupling introduces sensitivity to evidence placement and ties inference latency linearly to document length. We introduce PARSER, which decouples reading from reasoning.
By Kun Li, Zexuan Qiu, Tianhua Zhang · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.