Multi-hop question answering requires retrieving and integrating multiple pieces of evidence distributed across documents. Recent graph-based methods improve multi-hop reasoning through graph traversal over relational evidence structures. However, existing methods rely on independent path ranking during evidence organization, which often produces redundant and reasoning-incomplete evidence sets due to substantial structural overlap among selected graph paths. In this work, we argue that graph-based evidence organization may, to some extent, be formulated as a constrained evidence subgraph optimization problem. Based on this perspective, we propose CROG, a coverage-aware reasoning optimization framework that performs marginal-gain-based path selection to favor previously uncovered reasoning steps while suppressing redundant evidence, with node-budget and connectivity constraints to encourage compact and coherent evidence subgraphs. Experiments on multiple benchmarks demonstrate that CROG achieves superior reasoning performance while using fewer evidence units on average, and analysis based on exhaustive optimal search further validates the effectiveness of the greedy optimization strategy.

Adaptive learning focuses on recommending personalized materials (e.g., exercises, courses) to the unique needs of learners. Despite significant research, these methods still lag behind real teachers including two main limitations: (1) Prior methods model learner-item interactions based only on ID sequences, leading to insufficient use of both learner and item information, particularly the inability to leverage semantic content from item text; (2) The data-driven reinforcement learning frameworks struggle with stable performance in scenarios with sparse learning logs. To address these challenges, we introduce the Retrieval-enhanced Agent for Adaptive Learning (ReAL) powered by large language models (LLMs), to simulate teacher decision-making with extensive prior knowledge and teaching experience. Specifically, we approach the simulation from both internal and external perspectives. From the internal perspective, we utilize the superior natural language standing ability of LLMs to analyze item texts and learner profiles. This mechanism contributes to the generation of personalized and appropriate item candidates. From the external perspective, we simulate the teacher experience by retrieving similar learners, further ensuring the model’s performance on sparse interaction data. Furthermore, we design a reflector based on learners’ feedback to refine the recommendation process. Evaluation on three real-world datasets demonstrates the superiority of ReAL in both data utilization, recommendation accuracy and stability compared to various representative baselines.