What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Free-form communication in LLM-based multi-agent systems inflates token usage. This paper analyzes five strategies, proposes PACT protocol that compacts agent outputs into action-state records, improving performance-cost trade-off in coding tasks.
[2606.05304] What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
[Submitted on 3 Jun 2026]
Title:What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
View a PDF of the paper titled What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems, by Chen Huang and Yuhao Wu and Wenxuan Zhang
View PDF HTML (experimental)
Abstract:Multi-agent systems (MAS) built on large language models 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 this https URL.
Comments: 13 pages, 5 figures
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.05304 [cs.AI]
(or arXiv:2606.05304v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.05304
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Chen Huang [view email] [v1] Wed, 3 Jun 2026 18:00:22 UTC (800 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems, by Chen Huang and Yuhao Wu and Wenxuan Zhang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)