KnotBench benchmark shows state-of-the-art VLMs perform near random on diagrammatic knot reasoning tasks and lack ability to simulate structural moves.
Lake, Tomer D
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6roles
background 2polarities
background 2representative citing papers
ML climate emulators degrade under seasonal distribution shifts that proxy long-term climate change, but physically motivated compositional decompositions improve out-of-distribution performance with modest in-distribution trade-offs.
SciCrafter benchmark shows frontier AI agents plateau at 26% success on parameterized Minecraft redstone tasks requiring discovery and application of causal regularities, with knowledge application as the largest gap but gap identification emerging as a new hurdle for top models.
CogInstrument represents human reasoning as revisable cognitive motifs in graphical form to support iterative alignment with LLMs during planning tasks, with a N=12 study indicating gains in targeted revision, agency, and trust over standard dialogue interfaces.
The paper claims that alignment requires treating AI as part of the self through cognitive co-regulation, identifying risks like deskilling and automation bias while drawing on System 0 cognition theory.
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
citing papers explorer
-
The Gordian Knot for VLMs: Diagrammatic Knot Reasoning as a Hard Benchmark
KnotBench benchmark shows state-of-the-art VLMs perform near random on diagrammatic knot reasoning tasks and lack ability to simulate structural moves.
-
No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
ML climate emulators degrade under seasonal distribution shifts that proxy long-term climate change, but physically motivated compositional decompositions improve out-of-distribution performance with modest in-distribution trade-offs.
-
Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft
SciCrafter benchmark shows frontier AI agents plateau at 26% success on parameterized Minecraft redstone tasks requiring discovery and application of causal regularities, with knowledge application as the largest gap but gap identification emerging as a new hurdle for top models.
-
CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks
CogInstrument represents human reasoning as revisable cognitive motifs in graphical form to support iterative alignment with LLMs during planning tasks, with a N=12 study indicating gains in targeted revision, agency, and trust over standard dialogue interfaces.
-
Position: AI as Part of Self -- Extending the Mind Requires Cognitive Co-Regulation
The paper claims that alignment requires treating AI as part of the self through cognitive co-regulation, identifying risks like deskilling and automation bias while drawing on System 0 cognition theory.
-
Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.