Dynamic reasoning trees can help large language models solve complex tasks by explicitly structuring intermediate decisions.However, existing approaches often rely on manually specified subproblems or predefined decomposition patterns, which limits the effectiveness of reasoning and generalization.To solve this problem, we propose SyRA, a hierarchical reasoning framework based on MFR theory that supports the construction of adaptive reasoning trees and reliable error correction within a single LLM.Specifically, SyRA focuses on reasoning-tree construction, dynamically controlling branching and expansion using MFR principles to enable informative, non-redundant subproblem decomposition.In addition, it introduces a residual backtracking mechanism for adaptive cross-layer error correction, allowing the model to revise earlier reasoning decisions based on downstream feedback.Across eight reasoning benchmarks, SyRA significantly reduces logical errors and improves reasoning accuracy, while achieving a better balance between accuracy and reasoning time than the Chain-of-Thought, Decompose-Analyze-Rethink and Tree-of-Thought.Our

The development of data analytics services has fueled many optimizations in data scans, and indexes are one of the most important techniques to improve scan efficiency. Meanwhile, block-based data organization has become standard practice in these services, providing an opportunity for more fine-grained index selection at the block level. However, today’s systems ignore data distribution differences among blocks and usually tune indexes over the entire database table, leading to unnecessary storage costs and potential degradation in query performance. To bridge this gap, we propose BISLearner, a fast, block-aware index selecting approach based on reinforcement learning. One major challenge lies in differentiating the data distribution among data blocks. To solve this problem, BISLearner maintains simplified histograms that represent the data distribution of each block. When a query is issued, BISLearner leverages the query predicate and histogram-based block summaries to generate a specific workload representation for each block. However, such block-aware workload representation leads to an excessive number of input features, resulting in a slow or even incorrect convergence of neural networks. Inspired by the human-learning process, where more attention is devoted to the important parts of data, we design an attention-based neural model to efficiently handle the high volume of input features caused by table partitioning and select the best-suited index combinations at the block level. Additionally, to handle the expensive search space caused by attribute combinations and data partitioning, we employ heuristic-based invalid action masking at the block level to accelerate the training process. Our evaluation using PostgreSQL and Greenplum database systems demonstrates BISLearner is able to reduce job completion time by up to 28.45% compared to its best counterparts.

Modern data analytics services are coupled with external data storage services, making I/O from remote cloud storage one of the dominant costs for query processing. Techniques such as columnar block-based data organization and compression have become standard practices for these services to save storage and processing cost. However, the problem of effectively skipping irrelevant blocks at low overhead is still open. Existing data-skipping efforts maintain lightweight summaries (e.g., min/max, histograms) for each block to filter irrelevant data. However, such techniques ignore patterns in real-world data, enabling ineffective use of the storage budget and may cause serious false positives. This paper presents Sieve, a learning-enhanced index designed to efficiently filter out irrelevant blocks by capturing data patterns. Specifically, Sieve utilizes piece-wise linear functions to capture block distribution trends over the key space. Based on the captured trends, Sieve trades off storage consumption and false positives by grouping neighboring keys with similar block distributions into a single region. We have evaluated Sieve using Presto, and experiments on real-world datasets demonstrate that Sieve achieves up to 80% reduction in blocks accessed and 42% reduction in query times compared to its counterparts.

Modern data analytics platforms are often coupled with external data storage services such as Amazon S3, resulting in storage bottlenecks. Existing caching and prefetching solutions use higher-level information from data analytics frameworks, such as job dependency graphs(e.g., DAGs) and historical run time information, to predict future data accesses and then prefetch data into the cache and manage the cache contents based on those predictions.However, in doing so, they are not taking advantage of a fundamental opportunity: rather than caching data given a prediction of job execution, we can actually influence the job execution order to enable more effective caching and prefetching. With this key insight, we devise a set of novel heuristics and then design a system Tripod, which harmonizes job scheduling and data caching for analytics frameworks. With the higher-level information from analytics frameworks, Tripod explores a best-suited job execution order for prefetching and caching guided by the devised heuristics.We have implemented Tripod as extensions to Apache YARN and Tez. Our evaluation using standard analytic benchmarks (TPC-H and TPC-DS) shows that Tripod achieves up to 1.7x speedup over state-of-the-art approaches.