What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Quick Answer
The PACT protocol enhances multi-agent systems by optimizing inter-agent communication, reducing token usage while maintaining performance.
Quick Take
It improves task performance with fewer tokens across various MAS topologies, achieving a 10% reduction in tokens-per-resolved for OpenHands and halving input tokens for SWE-agent.
Key Points
- PACT treats inter-agent communication as a public state-update problem.
- It consistently improves performance-cost trade-offs in .
- OpenHands sees a 10% reduction in tokens-per-resolved with PACT.
- SWE-agent maintains resolve rates while halving input tokens.
- The code for PACT is publicly available on GitHub.
Paper Resources
Source Excerpt
arXiv:2606. 05304v1 Announce Type: new Abstract: (MAS) built on are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system performance and inference cost.
We analyze five common inter-agent communication strategies across two MAS topologies, finding that no fixed strategy is universally optimal. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for Agents
RAIL Guard introduces a closed-loop AI pipeline for large language models (LLMs) that evaluates outputs across eight dimensions and iteratively remediates failures, achieving 96.9% convergence compared to 49.1% for traditional block-and-retry methods. The system reduces unsafe agent executions by 33% without impacting task completion and is available as open-source SDKs.