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.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
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.
arXiv:2606. 03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and reason about the planning problems they are solving?
arXiv:2606. 14574v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments.
arXiv:2607. 02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from small language models (SLMs) that carry broad reasoning priors.
arXiv:2606. 27806v3 Announce Type: replace Abstract: Language agents plan by generating not only actions but also implicit predictions of how the world will change.
arXiv:2606. 16432v1 Announce Type: cross Abstract: User instructions are often underspecified because humans rely on implicit assumptions about the surrounding environment.