AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

VERITAS: A Multi-agent Co-scientist for Verifiable Image-Derived Hypothesis Testing

Lucas Stoffl, Benedikt Wiestler, Johannes Paetzold

ECCV 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies · 3 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
add multi-agent discussion over single-model pipeline (SMe to Veritas)SMe pipeline, local · 64-hypothesis benchmark, majority voteverdict accuracy: 71.2% vs. 61.0%Improved
add multi-agent discussion over single-model pipeline (SMe to Veritas)SMe pipeline, frontier · 64-hypothesis benchmark, majority voteverdict accuracy: 81.4% vs. 61.0%Improved
add code execution to direct reasoning (SMa to SMb)SMa direct reasoning · 64-hypothesis benchmarkverdict accuracy: 56.1 -> 63.8Improved
add iterative self-correction (SMc to SMd)SMc code via API · 64-hypothesis benchmarkevidence-label accuracy: +7.3 local, +11.8 frontierImproved
add iterative self-correction (SMc to SMd)SMc code via API · 64-hypothesis benchmarkverdict accuracy: +2.8 local, +3.8 frontierImproved
add structured phase guidance (SMd to SMe)SMd agentic, frontier · 64-hypothesis benchmarkverdict accuracy: 76.6 -> 65.5Hurt
halve context window to 8k from 16k (ablation)Veritas local · UCSF-PDGMevidence-label accuracy: -7.7pp (36.7 -> 29.0)Hurt
extend context window to 32k from 16k (ablation)Veritas local · UCSF-PDGMevidence-label accuracy: -5.0pp (36.7 -> 31.7)Hurt
set temperature to zero instead of 0.2 (ablation)Veritas local · UCSF-PDGMevidence-label accuracy: -9.0pp (36.7 -> 27.7)Hurt
add critic during execution phases (ablation)Veritas local · 64-hypothesis benchmark combinedverdict accuracy: +1.8pp combined verdict (71.4 vs 73.2 without critic)No clear effect
extend critic to planning and interpretation phases (ablation)Veritas local · 64-hypothesis benchmark combinedevidence-label accuracy: -10.2pp evidence, -4.9pp verdictHurt
use GT expert masks instead of SAT-Nano masks (ablation)Veritas local · UCSF-PDGMevidence-label accuracy: -23.7pp (36.7 -> 13.0)Hurt

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