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
Article Content
From source RSS / original summaryarXiv: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. Instead, effective inter-agent messages consistently preserve action-centered information needed by downstream agents.
Building on this, we propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem and projects each raw agent output into a compact action-state record before it enters shared history. Across different MAS topologies, PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens.
The gains extend to production coding harnesses: PACT lifts OpenHands' resolve rate at -10% tokens-per-resolved, and is resolve-neutral on SWE-agent while halving input tokens. Our code is publicly available at https://github. com/iNLP-Lab/PACT.
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 →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.