ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services

• URL: http://arxiv.org/abs/2606.28361v1
• Date: Sat, 13 Jun 2026 08:10:53 GMT
• Title: ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services
• Abstract summary: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering.<n>RAG causes historical documents and reasoning traces to accumulate across rounds, inflating cumulative input tokens.<n>This paper proposes ConCise, a training-free state-layer protocol that restructures cross-round context transmission.
• Score: 11.399162464271692
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deliver strong multi-hop accuracy. However, this paradigm causes historical documents and reasoning traces to accumulate across rounds, inflating cumulative input tokens approximately as $O(N^2)$ with progressively increasing noise density. In API-based service architectures, such growth directly amplifies per-request billing cost, network payload, and response latency. Existing compression approaches rely on pretrained modules or GPU-level KV cache access, introducing model hosting overhead incompatible with API-native, Serverless, and edge-side deployments. To address this issue, this paper proposes ConCise, a training-free state-layer protocol that restructures cross-round context transmission for multi-step RAG services. Specifically, ConCise replaces raw-text accumulation with an append-only chain of structured conclusions, compressing cumulative context growth from $O(N^2)$ to approximately $O(N)$. Furthermore, a fused generation mechanism is introduced to jointly emit reasoning and conclusions in a single API call, eliminating repeated input billing from serial dual-invocation overhead. Extensive experiments across twelve paired configurations spanning three models, two datasets, and two representative frameworks demonstrate that ConCise achieves 64.63\% average token savings while maintaining acceptable accuracy, providing a plug-and-play, deployment-friendly solution for cost-efficient multi-step RAG service optimization.

Related papers

• Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG [24.94881830262324]
  We propose DEX-Comp, a two-stage training recipe for RAG inference.<n>DEX-Comp compresses retrieved contexts by $16times$ and accelerates inference by $4times$--$24times$.<n>On five open-domain QA benchmarks at retrieval depths, DEX-Comp compresses retrieved contexts by $16times$ and accelerates inference by $4times$--$24times$.
  arXiv  Detail & Related papers  (2026-09-04T13:53:43Z)
• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning [14.508049757681862]
  LLM-powered coding agents spend the majority of their token budget reading repository files.<n>We show that this formulation creates a modeling bottleneck.<n>We propose LaMR, a structured pruning framework that decomposes code relevance into two interpretable quality dimensions.
  arXiv  Detail & Related papers  (2026-05-14T18:30:10Z)
• GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation [14.663434490160016]
  We present GenRec, a preference-oriented generative framework deployed on the JD App.<n>In month-long online A/B tests, GenRec achieves 9.5% improvement in click count and 8.7% in transaction count over the existing pipeline.
  arXiv  Detail & Related papers  (2026-04-16T11:07:05Z)
• Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs [0.0]
  This paper introduces emphCost-Aware RAG (CA-RAG), a per-query routing framework that selects from a discrete catalog of emphstrategy bundles<n>CA-RAG achieves textbf26% fewer billed tokens than always-heavy retrieval and textbf34% lower mean latency than always-direct inference.
  arXiv  Detail & Related papers  (2026-03-26T02:53:39Z)
• Stacked from One: Multi-Scale Self-Injection for Context Window Extension [69.24689919827817]
  modelname is a novel framework based on multi-grained context compression and query-aware information acquisition.<n>modelnameachieves performance superior or comparable to strong baselines.
  arXiv  Detail & Related papers  (2026-03-05T03:16:16Z)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• Cost-Aware Contrastive Routing for LLMs [57.30288453580456]
  We introduce Cost-Spectrum Contrastive Routing (CSCR), a lightweight framework that maps both prompts and models into a shared embedding space.<n>CSCR consistently outperforms baselines, improving the accuracy-cost tradeoff by up to 25%.
  arXiv  Detail & Related papers  (2025-08-17T20:16:44Z)
• Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification [83.25968588249776]
  We present a novel framework that combines over-approximation techniques from LiRPA-based approaches with a sampling-based method to compute tight intermediate reachable sets.<n>With negligible computational overhead, $textttPT-LiRPA$ exploiting the estimated reachable sets, significantly tightens the lower and upper linear bounds of a neural network's output.
  arXiv  Detail & Related papers  (2025-07-07T18:45:53Z)
• BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
  Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge.<n>This paper presents BRIEF, a lightweight approach that performs query-aware multi-hop reasoning.<n>Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
  arXiv  Detail & Related papers  (2024-10-20T04:24:16Z)
• Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems [42.137278756052595]
  $texttAgentPrune$ can seamlessly integrate into mainstream multi-agent systems. textbf(I) integrates seamlessly into existing multi-agent frameworks with $28.1%sim72.8%downarrow$ token reduction. textbf(III) successfully defend against two types of agent-based adversarial attacks with $3.5%sim10.8%uparrow$ performance boost.
  arXiv  Detail & Related papers  (2024-10-03T14:14:31Z)
• Implicit Grid Convolution for Multi-Scale Image Super-Resolution [6.8410780175245165]
  We propose a multi-scale framework that employs a single encoder in conjunction with Implicit Grid Convolution (IGConv) Our framework achieves comparable performance to existing fixed-scale methods while reducing the training budget and stored parameters three-fold.
  arXiv  Detail & Related papers  (2024-08-19T03:30:15Z)

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.