Pith. sign in

REVIEW 1 cited by

RMM: A Recursive Mental Model for Dialog Navigation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.00728 v2 pith:ZPVOOEXP submitted 2020-05-02 cs.CL cs.AIcs.CVcs.LGcs.RO

RMM: A Recursive Mental Model for Dialog Navigation

classification cs.CL cs.AIcs.CVcs.LGcs.RO
keywords agentanswersquestionsguidingnavigationanswermentalmodel
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent dialogue where robots need to both ask and answer questions.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs

    cs.RO 2025-12 conditional novelty 6.0

    VL-LN Bench turns instance-goal navigation into an interactive dialog task, contributes a 41k-trajectory house-scale benchmark with a GPT-4o oracle, and shows active questioning improves embodied agents' success.