Model Releases
Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?
arXiv:2610.03769v1 Announce Type: new Abstract: Multi-agent LLM systems pair a sender with broad context and an executor with a limited local view. We study when a short message improves the executor'
arXiv:2610.03769v1 Announce Type: new Abstract: Multi-agent LLM systems pair a sender with broad context and an executor with a limited local view. We study when a short message improves the executor's next decision, when raw context is preferable, and when a stronger sender helps. Our framework, receiver-relative bounded coordination, expresses message utility as receiver gain minus protocol tax. Compression beats raw context when tax savings exceed losses from omitted information and decoder mismatch. Even Bayes-sufficient compression can fail when a bounded executor cannot use its surface form. A three-stage decomposition separates externalization, absorption, and action closure, explaining how errors remain after the correct content reaches the receiver. Under a single-crossing condition, sender upgrades help above a receiver-burden threshold. Across six benchmarks, the same Qwen protocol raises ContextBench joint accuracy from 0.633 to 0.775 but lowers ToolSandbox from 0.889 to 0.653. Fixed-message replay reveals closure failures despite correct artifact recovery. These results guide an inference-time selector that improves the accuracy-cost frontier on the evaluated communication regimes.
Related
- RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough
- Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
- When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression
- HM-ROUTER: Joint Model and Harness Routing for Agentic Systems
Source: arXiv cs.LG | 2026-10-06