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%.
LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language
4 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 4roles
other 1polarities
unclear 1representative citing papers
OOPrompt reifies user intents into structured manipulable artifacts to enable modular and iterative prompting in LLM-based interactive systems.
PICCO is a five-element reference architecture (Persona, Instructions, Context, Constraints, Output) for structuring LLM prompts, derived from synthesizing prior frameworks along with a taxonomy distinguishing prompt concepts.
PRISM proposes a multi-agent system decoupling speech-to-prosody handling, LLM-based response generation, and synthesis, reporting metric improvements in empathy and prosodic fit for spoken dialogue.
citing papers explorer
-
OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting
OOPrompt reifies user intents into structured manipulable artifacts to enable modular and iterative prompting in LLM-based interactive systems.