benchmark · first seen 8 Oct 2026
ARC-AGI
Also: ARC, Abstraction and Reasoning Corpus
An interactive benchmark of abstract reasoning puzzles testing generalization to novel tasks.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual LearningPapers · 8 Oct 2026 · Chen Wu, Josh Passenger, Yin Song
- Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRMPapers · 9 Oct 2026 · Adrien Deliege, Marc Van Droogenbroeck
- When the harness decides success: state that cannot be re-observedPapers · 19 Oct 2026 · Raimondas Lencevicius
- Nested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URMPapers · 19 Oct 2026 · Sara Neri, Eugenio Gaeta, Andrea Ceschini, Andrea Facchinetti, Giuseppe Fico
- ARCANA: A Benchmark for Abstraction and Analogical ReasoningPapers · 21 Oct 2026 · Ruqi Chen, Zilei Wang, Wei Wang
- Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3Papers · 21 Oct 2026 · Jens Lehmann, Sahar Vahdati
Latest sources
- Continual-ARC: Measuring Skill Acquisition over a Working LifetimePapers · 10 Nov 2026 · Daniel Lenton, Yusha Arif, Haris Mahmood
- Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary ComputationPapers · 10 Nov 2026 · Luca Favole, Giorgio Mongardi, Giovanni Squillero, Alberto Tonda
- Rules, Traces and Routing Statistics: Training and Calibration Data for Open Models on ARC-AGI-2Papers · 4 Nov 2026 · Nguyen Minh Thang, Trinh Thi Phuong
- Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3Papers · 4 Nov 2026 · Harsidak Singh Banwait
- ConceptARC at Scale: Studying Conceptual Understanding in Reasoning ModelsPapers · 4 Nov 2026 · Philipp Mondorf, Adrien Deliège, Solim LeGris, Claas Beger, Ryan Yi, Barbara Pl…
- Beyond Answers, Traces, and Efficiency: Evidence for Adaptive ReasoningPapers · 2 Nov 2026 · Sejin Kim, Sundong Kim
- Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3Papers · 21 Oct 2026 · Jens Lehmann, Sahar Vahdati
- ARCANA: A Benchmark for Abstraction and Analogical ReasoningPapers · 21 Oct 2026 · Ruqi Chen, Zilei Wang, Wei Wang
- Nested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URMPapers · 19 Oct 2026 · Sara Neri, Eugenio Gaeta, Andrea Ceschini, Andrea Facchinetti, Giuseppe Fico
- When the harness decides success: state that cannot be re-observedPapers · 19 Oct 2026 · Raimondas Lencevicius
- Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRMPapers · 9 Oct 2026 · Adrien Deliege, Marc Van Droogenbroeck
- Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual LearningPapers · 8 Oct 2026 · Chen Wu, Josh Passenger, Yin Song