AI Paper Atlas

Research map / Continual learning / Class-incremental

Lifelong Learning with Behavior Consolidation for Vehicle Routing

Jiyuan Pei, Yi Mei, Jialin Liu, Mengjie Zhang, Xin Yao

ICLR 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 0 citations (OpenAlex)

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 CaEW (confidence-aware experience weighting) instead of equal weights (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 5.2 -> 4.9Improved
use decision-seeking behavior consolidation instead of KLD (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 5.5 -> 4.9Improved
buffer experiences only at the last epoch of each task instead of every epoch (ablation)LLR-BC · CVRP task order 1AF (x1e-3): 3.1 -> 0.6Improved
buffer one step as an experience instead of all steps of an instance (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 35.4 -> 4.9Improved
use variance instead of entropy for decision confidence (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 4.8 -> 4.9No clear effect
use variance instead of top-2 margin for decision confidence (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 4.8 -> 4.9No clear effect
keep original reservoir sampling instead of rescaled probabilities (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 4.9 -> 4.9No clear effect
set alpha to 10 instead of default (ablation)LLR-BC · CVRP task order 1AP (x1e-3): 4.9 -> 13.2Hurt
use LLR-BC instead of fine-tuning with Omni base solverOmni · CVRP lifelongAP (x1e-3): 34.7 -> 16.5Improved
use LLR-BC instead of fine-tuning with INViT base solverINViT · TSP lifelongAF (x1e-3): 0.6 -> 4.5Hurt
use LLR-BC instead of fine-tuningFine-tuning · CVRP lifelong (mean over 5 task orders)AP (x1e-3): 23.5 -> 4.2Improved
use LLR-BC instead of EWCEWC · TSP lifelong (mean over 5 task orders)AP (x1e-3): 18.3 -> 3.4Improved

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