HarnessEval-W: Agentifying the Evaluation of Visual Worlds
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, where judging a rollout requires understanding whether physics, causality, and world state evolve correctly. Humans spot such violations naturally, yet no existing benchmark automates this capability: metrics are computed brute-force, leaving no reasoning chain that can be examined or verified. We introduce HarnessEval-W, an agentified evaluation pipeline that brings the harness paradigm from the LLM ecosystem to worl
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%New benchmark exposes reasoning gaps in top models →
- PossiblePossibly related (embedding) · 53%Into the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning →
- FuzzySimilar title/name (fuzzy) · 87%strands-agents/harness-sdk →
“Fuzzy title match (0.94): “HarnessEval-W: Agentifying the Evaluation of Visual Worlds” ≈ “strands-agents/harness-sdk””
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: luo”
- FuzzyOverlapping authors or contributors · 62%google-research/google-research →
“Shared author/contributor keys: sun”
- FuzzyOverlapping authors or contributors · 62%mudler/LocalAI →
“Shared author/contributor keys: guo”
- LinkedLinked via arxiv author · 85%Weiliang Chen →
“HarnessEval-W: Agentifying the Evaluation of Visual Worlds”