AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration

Binqi Chen, Hongjun Ding, Ning Shen, Taian Guo, Jinsheng Huang, Luchen Liu, Ming Zhang

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration

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 early stopping alone to plain GFlowNet (ablation)GFlowNet alpha miner · CSI300Sharpe ratio: 0.72 -> -0.11Hurt
replace LSTM sequence encoder with GNN (RGCN) encoder (ablation)GFlowNet + ES · CSI300IC: 0.046 -> 0.070Improved
replace LSTM with GNN encoder (ablation)GFlowNet + ES · CSI300Sharpe ratio: -0.11 -> 1.25Improved
add structure-aware reward (ablation)GFlowNet + ES + GNN · CSI300Sharpe ratio: 1.25 -> 1.14; MDD -19.4% -> -17.6%Mixed
add novelty reward (ablation)GFlowNet + ES + GNN + SA · CSI300Sharpe ratio: 1.14 -> 1.53Improved
add entropy regularizer (ablation)AlphaSAGE · CSI300Sharpe ratio: 1.53 -> 1.71Improved
add entropy regularizer (ablation)AlphaSAGE · CSI300RICIR: 0.614 -> 0.583Hurt
use AlphaSAGE instead of best baselinesalpha mining · CSI500ICIR: 0.396 -> 0.379No clear effect
increase novelty reward weight beyond moderate levels (ablation)AlphaSAGE · CSI300correlation and portfolio metricsMixed

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