The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Effective collaboration requires language models to understand what others know and believe, and to act accordingly. Models that assume others share their information may omit necessary communication...
arXiv:2606. 31422v1 Announce Type: new Abstract: Long-horizon language agents do not only choose actions; they carry a private model of the world from one decision to the next.
arXiv:2606. 31422v2 Announce Type: replace Abstract: Language agents acting over long horizons must maintain beliefs about tool states, object locations, graph edges, and subgoal dependencies.
BASIS is a benchmark that tests large language model agents on their ability to infer users’ mental states, detect belief‑reality mismatches, and use this insight to craft better solutions in interactive settings. The study shows that current models often ignore users’ mental states, leading to poorer outcomes, while explicitly eliciting and incorporating such information improves solution quality. Additional experiments compare BASIS with Chain‑of‑Thought prompting, targeted training, and multi‑agent collaboration to demonstrate the practical benefits of mental‑state awareness.
arXiv:2610.19215v1 Announce Type: new Abstract: Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents...
Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the request --- risking misalignment with the user --...