mlsanityData to 7 Oct 2026

Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents

arXiv 2608.22237 ↗First posted 23 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute task-relevant evidence, while existing context-reduction methods mainly intervene after broad content has already entered the trajectory. We present SparseRead, a training-free, model-transparent reading layer that controls content admission before unnecessary evidence reaches the model context. SparseRead combines a regime-aware Read Gate, extensible Reader Backends, and a stateful protocol for bounded, source-anchored evidence acquisition with explicit refinement, verification, stopping, and fallback. Across six frontier models, including Claude Opus 5, and five workload scenarios, SparseRead reduces token volume by up to 92.9% and wall time by up to 89.0%, while preserving or improving task quality. Its consistent gains across three agent frameworks further demonstrate broad portability.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 23 Aug 2026.

Builds on

21 of 26 references.

References · 21

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  3. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  4. 2024SnapKV: LLM Knows What You are Looking for Before Generationcited by 848
  5. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cachecited by 604
  6. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  7. 2024PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funnelingcited by 420
  8. 2023Learning to Compress Prompts with Gist Tokenscited by 379
  9. 2023Adapting Language Models to Compress Contextscited by 350
  10. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 343
  11. 2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 255
  12. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 200
9 more
  1. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agentscited by 126
  2. 2024ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identificationcited by 86
  3. 2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 44
  4. 2025The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Managementcited by 40
  5. 2026SWE-Pruner: Self-Adaptive Context Pruning for Coding Agentscited by 40
  6. 2026A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compressioncited by 12
  7. 2025ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelismcited by 7
  8. 2026KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Servingcited by 7
  9. 2026CoACT: Action-Preserving Observation Compression for Coding Agentscited by 4

Built on by

Not cited yet.