User-turn generation reveals that LLMs' interaction awareness is largely decoupled from task accuracy, remaining near zero in deterministic settings even as accuracy scales to 96.8% on GSM8K.
Aligning language models from user interactions.arXiv preprint arXiv:2603.12273
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
NanoResearch introduces a tri-level co-evolving framework of skills, memory, and policy to personalize LLM-powered research automation across projects and users.
citing papers explorer
-
Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
User-turn generation reveals that LLMs' interaction awareness is largely decoupled from task accuracy, remaining near zero in deterministic settings even as accuracy scales to 96.8% on GSM8K.
-
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
NanoResearch introduces a tri-level co-evolving framework of skills, memory, and policy to personalize LLM-powered research automation across projects and users.