From the Archive
Briefs
Periodic reading lists pairing recent LLM/AI papers with related research from the collection.
-
2026-06-22
Retrieval Collapses When AI Pollutes the Web · The Ghost Couple: Correlated LLM Name Priors and Their Haunting of the Web and Academic Publishing · An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
-
2026-06-16
From AGI to ASI · q0: Primitives for Hyper-Epoch Pretraining · Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal · +2 more
-
2026-06-09
Argument Collapse: LLMs Flatten Long-Form Public Debate · Steering LLM Viewpoints through Fabricated Evidence Injection · Reasoning Structure of Large Language Models · +4 more
-
2026-05-31
Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer? · Agentic Systems as Boosting Weak Reasoning Models · Scaling Laws for Agent Harnesses via Effective Feedback Compute · +3 more
-
2026-05-28
From Simulation to Enaction: Post-trained language models recognize and react to their own generations · Foundation Protocol: A Coordination Layer for Agentic Society · Look Before You Leap: Autonomous Exploration for LLM Agents · +2 more
-
2026-05-27
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning · Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrence · SkillOpt: Executive Strategy for Self-Evolving Agent Skills
-
2026-05-20
There Will Be a Scientific Theory of Deep Learning · Can AI Agents Agree? · Useful Memories Become Faulty When Continuously Updated by LLMs · +1 more
-
2026-05-19
There Will Be a Scientific Theory of Deep Learning · Can AI Agents Agree? · Useful Memories Become Faulty When Continuously Updated by LLMs · +1 more