AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval

Yu Liu, Yanbing Liu, Fangfang Yuan, Cong Cao, Youbang Sun, Kun Peng, WeiZhuo Chen, Jianjun Li, Zhiyuan Ma

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 4 citations (OpenAlex)

Read the paper

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 the Plan Agent (ablation)OPERA · MuSiQueEM: 17.1 -> 39.7Improved
add the Rewrite Agent (ablation)OPERA · MuSiQueEM: 34.5 -> 39.7Improved
keep both Plan and Rewrite Agents (ablation)OPERA · MuSiQueEM: 16.7 -> 39.7Improved
train with SFT instead of CoT prompting (ablation)OPERA architecture · MuSiQueEM: 21.2 -> 24.3Improved
train with GRPO instead of SFT (ablation)OPERA architecture · MuSiQueEM: 24.3 -> 34.8Improved
use MAPGRPO (role-specific rewards, sequential training) instead of standard GRPO (ablation)OPERA architecture · MuSiQueEM: 34.8 -> 39.7Improved
train with SFT instead of CoT (ablation)OPERA architecture · NQ (single-hop, out-of-domain)EM: 23.1 -> 19.5Hurt
train with MAPGRPO instead of CoT (ablation)OPERA architecture · NQ (out-of-domain)EM: 23.1 -> 36.6Improved
train with MAPGRPO instead of CoT (ablation)OPERA architecture · MultiHopRAG (out-of-domain)EM: 42.3 -> 55.7Improved
inject high-scoring expert samples into each GRPO group (25%) (ablation)MAPGRPO training (7B) · gradient variancepolicy gradient varianceImproved

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