Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents
cs.AI
Submitted: 2026-08-23
Updated: 2026-11-07
Code: https://github.com/Zedong-Liu/SparseReading
Terminology
Sources
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- CoACT: Action-Preserving Observation Compression for Coding Agents
- Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
- LooGLE: Can Long-Context Language Models Understand Long Contexts?
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents