A shared vocabulary between cognitive science and LLM research is established and a fine-grained evaluation framework is introduced, enabling diagnosis of reasoning failures and principled development of models that reason through robust cognitive mechanisms rather than spurious shortcuts, while providing tools to test...
S. Li, Priyanka Kargupta, Hao-Cheng Wang et al.· arXiv.org· 26 citations· ⚡2
This work introduces AGNI, an automated pipeline that extracts trajectory-relevant assumptions, injects targeted environmental changes, and validates that the resulting novel tasks remain solvable and highlights a gap between task competence and adaptive capability and motivate environmental variation as a core dimensi...
This work presents SocialRL, a general recipe that trains social reasoning directly, and applies it to a 4B model across six domains: Deal-or-No-Deal, CaSiNo, Craigslist, Job Interview, Calendar, and Marketplace, finding that in-domain training reaches the frontier.
Wenyue Hua, Zachary Huang, Tyler Payne et al.· 0 citations
This work presents Collaborative Reasoner, a framework to evaluate and improve the collaborative reasoning abilities of language models, and proposes a self-play method to generate synthetic multi-turn preference data and further train the language models to be better collaborators.
Ansong Ni, Ruta Desai, Yang Li et al.· Neural Information Processin...· 7 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.