Tag
Ratel is an open-source tool that reduces input tokens by 79% and improves tool selection accuracy for AI agents by loading only needed tools using a BM25 index, instead of all available tools.
This paper introduces BabelTele, a compressed writing style that uses abbreviations, symbols, and mixed-language fragments to reduce text length by 72.1% while preserving 99.5% semantic fidelity for LLMs, arguing that human readability and machine recoverability are separable.
This paper introduces 'constant-context skill learning,' a framework that moves procedural knowledge from prompts into model weights to reduce token usage and improve privacy for LLM agents. The method achieves strong performance on benchmarks like ALFWorld and WebShop while significantly reducing inference costs.
This paper proposes the Experience Compression Spectrum, a unifying framework that integrates agent memory, skill discovery, and rule-based systems along a single axis of increasing compression (5-20× for episodic memory, 50-500× for procedural skills, 1000×+ for declarative rules). The work identifies a critical gap—the 'missing diagonal'—showing that existing systems operate at fixed compression levels without adaptive cross-level support, and articulates design principles for scalable, full-spectrum agent learning systems.