{"slug": "state-compression-in-two-agent-llm-relays-a-closed-world-study-of-constraint", "title": "State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation", "summary": "A study from arXiv finds that structured JSON extraction achieves 96% feasibility accuracy in two-agent LLM relays for travel planning, while narrative summarization drops feasibility to 48% despite producing the smallest payload. The closed-world experiment with Researcher and Booker agents shows that constraint preservation depends on auditable hand-off representations rather than brevity alone.", "body_md": "arXiv:2607.18265v1 Announce Type: cross\nAbstract: Long-running Large Language Model (LLM)-based agents often accumulate large intermediate traces containing audits, eliminations, and numeric calculations. In practice, this state is compressed before handing it to a downstream decision step, creating an information bottleneck in which small omissions can break strict numeric or categorical constraints. This paper evaluates hand-off compression in a closed-world travel-planning relay with two LLM agents. A Researcher audits a fixed inventory of hotels and flights for 50 goal instances, and a Booker selects a hotel--flight pair using only the goal and the hand-off payload, with the inventory withheld. We compare four hand-off conditions: no compression, narrative summarization, schema-constrained JSON extraction, and embedding-based pruning. Exhaustive enumeration over the fixed inventory provides exact feasible and optimal labels. Results show that hand-off representation strongly affects downstream feasibility under a small decision model. JSON extraction achieves the highest feasibility accuracy at 0.96, while narrative summarization, despite producing the smallest compressed hand-off payload, degrades feasibility to 0.48. Embedding-based pruning matches the uncompressed control on feasibility at 0.88 without an additional generative compression call. These findings indicate that constraint checking benefits from structured and auditable hand-off representations rather than relying on brevity alone.", "url": "https://wpnews.pro/news/state-compression-in-two-agent-llm-relays-a-closed-world-study-of-constraint", "canonical_source": "https://www.machinebrief.com/news/state-compression-in-two-agent-llm-relays-a-closed-world-stu-2xi0", "published_at": "2026-07-22 04:00:00+00:00", "updated_at": "2026-07-22 05:35:01.236364+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/state-compression-in-two-agent-llm-relays-a-closed-world-study-of-constraint", "markdown": "https://wpnews.pro/news/state-compression-in-two-agent-llm-relays-a-closed-world-study-of-constraint.md", "text": "https://wpnews.pro/news/state-compression-in-two-agent-llm-relays-a-closed-world-study-of-constraint.txt", "jsonld": "https://wpnews.pro/news/state-compression-in-two-agent-llm-relays-a-closed-world-study-of-constraint.jsonld"}}