AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Detecting Perspective Shifts in Multi-Agent Systems

Eric W Bridgeford, Hayden Helm

ICML 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use TDKPS embeddings with agent-level permutation test instead of DCorragent-level change detection (simulation) · Temporal Gaussian blobs, 5 agents, effect size 0.2power: DCorr power <0.15; TDKPS nearly quadruples itImproved
increase number of queries (ablation)DCorr agent-level test · Temporal Gaussian blobsType I errorHurt
increase number of response replicates (ablation)TDKPS agent-level test · Temporal Gaussian blobsType I error rate: 5--10% inflation decreases with more replicatesImproved
use sample-splitting variant TDKPS-C (ablation)TDKPS agent-level test · Temporal Gaussian blobsType I error and powerMixed
use TDKPS embeddings with paired energy test instead of DCorr or DCorr o TDKPSgroup-level change detection (simulation) · Temporal Gaussian blobs, SNR<<0.02powerImproved
increase agents per group from 10 to 80 (ablation)PE o TDKPS · Temporal Gaussian blobs, effect size 0.2power: ~50% at 10 agents -> >95% at 80 agentsImproved
use public health queries instead of orthogonal queriesTDKPS agent-level test on congressperson agents · COVID-19 natural experimentKendall tau with proximity to COVID-19: 0.01 -> 0.51Improved
use public health queries instead of general political queriesTDKPS agent-level test on congressperson agents · COVID-19 natural experimentKendall tau with proximity to COVID-19: 0.34 -> 0.51Improved
change embedding model (four architectures) (ablation)TDKPS temporal shift pattern · congressperson agentsSpearman rho of shift pattern: rho > 0.99No clear effect
change retrieval depth (ablation)TDKPS temporal shift pattern · congressperson agentsSpearman rho of shift pattern: rho > 0.81No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy