LLMs Corrupt Your Documents When You Delegate
A large-scale study on long-horizon document tasks.
Articles in the reference/papers subcategory
-
-
-
Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
Self-generated agent context files don't help.
-
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Self-generated skills don't help.
-
-
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Optimising computation at the token-level
-
-
-
NoProp: Training Neural Networks Without Back-Propagation or Forward-Propagation
an alternative training method to backprop that does local layer learning
-
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
learn to reason without any human-annotated data.
