TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
Prompt compression for large language models: A survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
GRC unifies generation, retrieval, and compression in LLMs via meta latent tokens for single-pass execution with modular flexibility.
citing papers explorer
-
TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
-
GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression
GRC unifies generation, retrieval, and compression in LLMs via meta latent tokens for single-pass execution with modular flexibility.