1.6k citations · 11.3k across the 73 of their papers we have counts for
3 papers · 1 filter
Transformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes
Khashayar Gatmiry, Nathan W. Henry, Chloe H. Su +5
We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depending on their initialization.…
The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella +1
When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositi…
ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context
Zidi Xiu, David Q. Sun, Kevin Cheng +9
Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assista…