ARC-AGI

Timeline

1. Oct 8, 2026 · Research paper · 2 sources
   Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
   We introduce Memento 3, building on the Memento series to enable frozen LLM agents to continually learn explicit world models through external memory.
2. Oct 8, 2026 · Research paper · 2 sources
   Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
   In this paper, we introduce InfiLoop, a loop-native residual connection that learns which past computations to retain and how much to accept from each new update.
3. Oct 8, 2026 · Research paper · 1 source
   Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning
   We study how a coding agent learns across a sequence of abstract reasoning tasks.
4. Oct 6, 2026 · Research paper · 1 source
   FreeEvolve: Learning to Evolve Beyond Fixed Loops
   Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand: a fixed search loop decides how candidates are evaluated, which are kept and when the search stops.
5. Oct 2, 2026 · Opinion / analysis · 1 source
   Academia is for Ambition — Alex Zhang, MIT
   Last call for regular tickets for AI Engineer NYC!
6. Sep 29, 2026 · Opinion / analysis · 1 source
   The Programming Language That Referees Mathematics — Leo de Moura
   Leonardo de Moura created Lean and co-created Z3.
7. Sep 29, 2026 · Opinion / analysis · 1 source
   [AINews] Opus 5.5 is good at explainer videos
   Opus 5.5 shipped this week but the vibes are overwhelmingly positive:

Often appears with