Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
Tom Zehle
LLM-based multi-agent systems have demonstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling, and retrieval-augmented gener…
cs.CL2026
promptolution: A Unified, Modular Framework for Prompt Optimization
Tom Zehle, Timo HeiÃ, Moritz Schlager +2
Prompt optimization has become crucial for enhancing the performance of large language models (LLMs) across a broad range of tasks. Although many research papers demonstrate its ef…
cs.CL2025
CAPO: Cost-Aware Prompt Optimization
Tom Zehle, Moritz Schlager, Timo Heià +1
Large language models (LLMs) have revolutionized natural language processing by solving a wide range of tasks simply guided by a prompt. Yet their performance is highly sensitive t…