Hidden Anchors in Multi-Agent LLM Deliberation
This paper proposes a dynamical system model for multi-agent LLM deliberation, where each agent has a hidden internal belief (anchor) that continuously pulls its opinion. The model explains a behavior forbidden by classical consensus rules: an agent's confidence can exceed the convex hull of initial beliefs. Experiments on three open-weight model families show that all anchors have similar influence but differ in location, and only when the anchor is far from initial opinions does deliberation escape the hull.
[2606.19494] Hidden Anchors in Multi-Agent LLM Deliberation
[Submitted on 17 Jun 2026]
Title:Hidden Anchors in Multi-Agent LLM Deliberation
View a PDF of the paper titled Hidden Anchors in Multi-Agent LLM Deliberation, by Apurba Pokharel and Ram Dantu
View PDF HTML (experimental)
Abstract:Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy, yet how and why it works is rarely modelled. Such deliberation mirrors how humans reach decisions. As social animals we are pulled both by the group, the herd effect that classical opinion-dynamics models such as DeGroot and Friedkin--Johnsen capture, and by our own internal belief, which they do not. We model multi-agent deliberation as a closed-loop dynamical system in which each agent carries a hidden internal belief, its anchor, that continually pulls its opinion regardless of its neighbours. We show this anchor can be recovered from the deliberation alone, and that it explains a behaviour classical consensus rules forbid: an agent's confidence in the correct answer can climb past where any agent started, escaping the space (convexhull) formed by the initial beliefs. Checking whether the recovered anchor also predicts held-out runs (generalizes) gives a simple test for when a model is truly driven bysuch an anchor. Across three open-weight model families this is a spectrum, not all-or-nothing. All anchors' influence are about equally strongly, but they differ in where the anchor sits, and only when it sits far from the initial opinions does deliberation escape the hull and need the full closed-loop model.
Comments: 13 pages, 6 figures, 7 tables
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.19494 [cs.AI]
(or arXiv:2606.19494v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.19494
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Apurba Pokharel [view email] [v1] Wed, 17 Jun 2026 18:29:27 UTC (763 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Hidden Anchors in Multi-Agent LLM Deliberation, by Apurba Pokharel and Ram Dantu
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?)