[2605.30136] Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
-->
Computer Science > Artificial Intelligence
arXiv:2605.30136 (cs)
[Submitted on 28 May 2026]
Title:Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
Authors:Hongxiang Zhang, Yuan Tian, Tianyi Zhang<br>View a PDF of the paper titled Enhancing Multi-Agent Communication through Attention Steering with Context Relevance, by Hongxiang Zhang and Yuan Tian and Tianyi Zhang
View PDF<br>HTML (experimental)
Abstract:LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to rapidly accumulate extremely long conversation histories during interaction. As conversations lengthen, relevant information is increasingly diluted by irrelevant context, leading to degraded performance. In this work, we present Agent-Radar, a training-free context management method that dynamically steers each agent's attention toward relevant context with a novel temporal and spatial decay mechanism. Our experiments demonstrate that Agent-Radar outperforms state-of-the-art methods across five different benchmarks, yielding gains of up to 7.64 absolute points. Furthermore, our analysis shows that Agent-Radar remains effective and robust as the number of agents and interaction rounds increases. Finally, the ablation study shows that core components in Agent-Radar are crucial to performance and generalizable in different settings.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:<br>arXiv:2605.30136 [cs.AI]
(or<br>arXiv:2605.30136v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.30136
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history<br>From: Hongxiang Zhang [view email]<br>[v1]<br>Thu, 28 May 2026 16:02:52 UTC (1,589 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Enhancing Multi-Agent Communication through Attention Steering with Context Relevance, by Hongxiang Zhang and Yuan Tian and Tianyi Zhang<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.AI
next >
new<br>recent<br>| 2026-05
Change to browse by:
cs
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
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? |<br>Disable MathJax (What is MathJax?)