AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

Preference Is More than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback

Shengbo Wang, Hong Sun, Ke Li

AAAI 2026 · Reinforcement learning › RL from feedback · approach: Reward modeling versus direct optimization · 1 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 augmented feedback (related observations) to confidence boundsRUCB / DTS · Sushi and Car Preference recommendationcumulative regretImproved
add augmented feedback to DTS/RUCB with LLM-annotated dependenciesRUCB / DTS · LLM response optimization (Anthropic H-H)cumulative regretImproved
use context-free DB instead of parametric BT-based DBdueling bandits · Sushi and Car Preferencecumulative regretImproved
use deterministic IPEA-RUCB instead of stochastic IPEA-DTSIPEA-HF · DTLZ7 multi-objective optimization (sparse feedback)cumulative regretImproved
use stochastic strategy (DTS-based) instead of deterministic RUCB-basedIPEA-HF · LLM response optimizationcumulative regretImproved

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