State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation
A preprint investigates how different state compression methods impact constraint preservation in a two-agent LLM relay for travel planning. The study finds that schema-constrained JSON extraction yields the highest feasibility accuracy (0.96), while narrative summarization significantly reduces it (0.48). Embedding-based pruning achieves feasibility accuracy comparable to the uncompressed baseline (0.88) without requiring additional generative calls.
Why it matters: The work demonstrates that structured, auditable hand-off formats are crucial for maintaining constraints in multi-agent LLM systems, challenging the notion that brevity alone is sufficient.
Full story at: arXiv AI/ML ↗