AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planning

Zixuan Chen, Xiangrong Feng, Jieqi Shi, Lin Shao, Jing Huo, Yang Gao

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add forward critic loss to the backward planner training (ablation)AGiLe · LIBERO-LONGaverage success rate (%): 89.0 -> 97.1Improved
add forward critic loss to the backward planner training (ablation)AGiLe · LIBERO-LONGperfectly solved tasks: 3 / 10 -> 7 / 10Improved
add affordance grounding via cross-attention (ablation)AGiLe · LIBERO-LONGaverage success rate (%): 90.5 -> 97.1Improved
add affordance grounding via cross-attention (ablation)AGiLe · LIBERO-LONGperfectly solved tasks: 2 / 10 -> 7 / 10Improved
AGiLe bidirectional planning with affordance versus backward-only LBPlatent backward planning · LIBERO-LONGaverage success rate (%): 88.6 -> 97.1Improved
AGiLe versus LBP on late stages of real-world 6-stage taskslatent backward planning · real-world long-horizon tasksstage-wise score: LBP falls to 5% (Task 3) and 2% (Task 4) in later stagesImproved
AGiLe versus LBP on 'Put both pots on stove'latent backward planning · LIBERO-LONG task 9success rate (%): 60.0 -> 78.6Improved
AGiLe versus Seer on perfect-task countforward-predictive planners · LIBERO-LONGtasks with 100% success: Seer 1, LBP 3, AGiLe 7 of 10Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy