Training-free navigation framework tops 76% success
HarnessVLN, a training-free embodied navigation framework, beats prior training-free methods on four benchmarks, per the authors, without independent review.
ImportanceLocalEvidenceE2 unreplicated
The training-free embodied navigation framework HarnessVLN reaches success rates of 60.8%, 53.9%, 76.0% and 59.3% on the R2R, RxR, HM3D-v2 and HM3D-OVON benchmarks, surpassing prior training-free methods — a new reference point for what training-free approaches can achieve.
Prior training-free methods required separately building perception, memory and execution pipelines, which were hard to coordinate. HarnessVLN uses a unified Agent Harness to coordinate perception, memory and execution tools, and the authors say it has been deployed on a humanoid robot.
These figures are self-reported by Yang Chen and co-authors and have not been independently reviewed.
The preprint was submitted to arXiv on September 14 and updated to v2 on the 16th; the results have not yet been independently reproduced.