PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

• URL: http://arxiv.org/abs/2609.06702v1
• Date: Sun, 06 Sep 2026 16:19:01 GMT
• Title: PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
• Abstract summary: We introduce PARSER, which decouples reading from reasoning.<n>A bank of lightweight subagents each bound to a single chunk read the entire document in parallel.<n>On multi-hop QA with contexts ranging from 7K to 896K tokens, PARSER with a 4B backbone outperforms the strongest sequential memory baseline.
• Score: 85.82624962221026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential 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. A bank of lightweight subagents each bound to a single chunk read the entire document in parallel, while a lead agent reasons in depth through iterative scatter--gather rounds: at each round it broadcasts a query to all subagents, aggregates the returned evidence, and formulates a deeper follow-up query conditioned on what has been found so far. This decoupled design concentrates all learnable behavior in the lead agent, which is optimized with reinforcement learning, while the subagents remain frozen off-the-shelf models. On multi-hop QA with contexts ranging from 7K to 896K tokens, PARSER with a 4B backbone outperforms the strongest sequential memory baseline by 5.7 points on average and by 12.0 points at 896K tokens. Scaling to a 9B backbone, PARSER surpasses DeepSeek-V4-Pro by 6.3 points. Controlled experiments confirm that PARSER is robust to perturbations in evidence position, order, and distance, conditions that cause large accuracy swings in sequential methods, while reducing inference latency by up to 11x.

Related papers

• REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling [0.0]
  REIGN is a bi-encoder that operates on sequences of contextualised chunk embeddings from a frozen Guidance Network (GN) rather than on raw tokens.<n>We release a synthetic long-document retrieval benchmark for contrastive training and evaluation at long context lengths.<n>A paired significance test puts it on par with models 1.6-4.3x larger on the patent task, and it stays within 0.65 nDCG@10 of a 20x-larger model on LoCo.
  arXiv  Detail & Related papers  (2026-08-30T16:50:38Z)
• Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving [0.28304882054363123]
  This work is the first to impose that identity as a constraint inside PTQTP's solver.<n>We apply this to the routed experts of DeepSeek-V4-Flash-0731, a 284B-A13B mixture-of-experts model.<n>All code, formats, and evaluation artifacts are open source in the fucina inference stack.
  arXiv  Detail & Related papers  (2026-08-09T20:53:47Z)
• PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory [30.188604861823823]
  We propose PI-Mem, a mechanism that processes chunks in parallel and iteratively refines a shared memory over a bounded number of turns.<n>We evaluate PI-Mem with Qwen3.5-35B-A3B and Qwen2.5-7B on the HotpotQA benchmark across context lengths up to 3.6 million tokens.
  arXiv  Detail & Related papers  (2026-08-04T02:59:16Z)
• Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation [59.438696079345426]
  DICE is a training-free document-side strategy that splits documents into chunks, encodes them independently with a frozen model, and aggregates them back into a single vector.<n>On LongEmbed, DICE improves retrieval across four backbones, with the largest gains on slices beyond 4k tokens.<n>Across 12,779 filtered samples, DICE yields lower EDI than the single-vector baseline in 92.8% of cases.
  arXiv  Detail & Related papers  (2026-06-17T07:44:04Z)
• How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study [6.9242874337023705]
  Retrieval-augmented generation pipelines rely on chunking to segment source files into retrievable units.<n>We present a controlled empirical study isolating the effect of chunking on code completion quality.<n>Our results reveal that chunking strategy has a statistically significant effect on RAG-based code completion.
  arXiv  Detail & Related papers  (2026-05-06T11:09:42Z)
• Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning [47.87361916374891]
  We propose a framework for efficient long-context inference based on chunk-wise compression and selective memory recall.<n>The framework segments long inputs into chunks and encodes each chunk into compressed memory representations using a learned compressor.<n>It achieves up to a 2 times reduction in peak GPU memory usage and a 6 times inference speedup over MemAgent.
  arXiv  Detail & Related papers  (2026-02-09T08:33:11Z)
• InfMem: Learning System-2 Memory Control for Long-Context Agent [43.413381779578266]
  InfMem is a control-centric agent that instantiates System-2-style control via a PreThink-Retrieve-Write protocol.<n>On ultra-long QA benchmarks from 32k to 1M tokens, InfMem consistently outperforms MemAgent across backbones.
  arXiv  Detail & Related papers  (2026-02-02T19:15:08Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• Rethinking Thinking Tokens: LLMs as Improvement Operators [80.12087211785949]
  Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which allows them to explore solution strategies with self-checking.<n>This results in higher accuracy, but inflates context length, token/compute cost, and answer latency.<n>We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier?<n>We identify an interesting inference family Parallel-Distill-Refine (PDR), which performs the following: (i) generate diverse drafts in parallel; (ii) distill them into a bounded, textual workspace; and (iii) refine conditioned on this workspace
  arXiv  Detail & Related papers  (2025-10-01T17:08:59Z)
• dParallel: Learnable Parallel Decoding for dLLMs [77.24184219948337]
  Diffusion large language models (dLLMs) offer parallel token prediction and lower inference latency.<n>Existing open-source models still require nearly token-length decoding steps to ensure performance.<n>We introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling.
  arXiv  Detail & Related papers  (2025-09-30T16:32:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.