We propose RLlib Flow, a hybrid actor-dataflow programming model for distributed RL, and validate its practicality by porting the full suite of algorithms in RLlib, a widely adopted distributed RL library.

Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against latency and token/tool budgets. This paper introduces Hierarchical Sequence (HSEQ) Iteration for Heterogeneous Question Answering, a unified framework that (i) linearize documents, tables, and knowledge graphs into a reversible hierarchical sequence with lightweight structural tags, and (ii) perform structure-aware iteration to collect just-enough evidence before answer synthesis. A Head Agent provides guidance that leads retrieval, while an Iteration Agent selects and expands HSeq via structure-respecting actions (e.g., parent/child hops, table row/column neighbors, KG relations); Finally the head agent composes canonicalized evidence to genearte the final answer, with an optional refinement loop to resolve detected contradictions. Besides, HSEQ exhibits three key advantages: (1) a format-agnostic unification that enables a single policy to operate across text, tables, and KGs without per-dataset specialization; (2) guided, budget-aware iteration that reduces unnecessary hops, tool calls, and tokens while preserving accuracy; and (3) evidence canonicalization for reliable QA, improving answers consistency and auditability. Large language models (LLMs), such as ChatGPT (Achiam et al., 2023), LLaMA (Dubey et al., 2024), Falcon (Zuo et al., 2025), have been increasingly relying on retrieval-augmented generation (RAG) to ground answers in external evidence. With reliable supplementary knowledge offered factual errors are reduced, especially in domain-specific questions, leading to higher accuracy and fewer hallucinations (Zhu et al., 2021b; Gao et al., 2023; Zhao et al., 2024). However they may fall with branchy plans, repeated web/file calls, and verbose chain-of-thought prompts, yielding unpredictable token/tool costs and latency; termination is often heuristic, leading to premature answers or extra wasted loops with budgets decoupled from the evidence actually inspected (Singh et al., 2025). Although existing heterogeneous RAG systems (Y u, 2022; Christmann & Weikum, 2024) are available to deal with multiple formats of data, they may still face issues in either weak alignment across representations or lossy and non-reversible serialization that obscures provenance and blocks faithful reconstruction. Hierarchical Sequence Iteration (HSEQ) for Heterogeneous Question Answering introduces a reversible hierarchical sequence interface that linearizes documents, tables, and KGs into a sequence of typed segments with lightweight structure (e.g., parent/child locality, offsets or coordinates, minimal schema/time tags).

When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two methods for further improvement in this setting. Both methods focus on combining rationales generated by a larger Language Model with longer contexts created from a multi-hop dense retrieval system. The first method ($\textit{RR}$) involves training a Rationale Ranking model to score both generated rationales and retrieved contexts with respect to relevance and truthfulness. We then use the scores to derive combined contexts from both knowledge sources using a number of combinatory strategies. For the second method ($\textit{RATD}$) we utilise retrieval-augmented training datasets developed by Hartill et al. 2023 to train a smaller Reasoning model such that it becomes proficient at utilising relevant information from longer text sequences that may be only partially evidential and frequently contain many irrelevant sentences. We find that both methods significantly improve results. Our single best Reasoning model materially improves upon strong comparable prior baselines for unseen evaluation datasets (StrategyQA 58.9 $\rightarrow$ 61.7 acc., CommonsenseQA 63.6 $\rightarrow$ 72.7 acc., ARC-DA 31.6 $\rightarrow$ 52.1 F1, IIRC 25.5 $\rightarrow$ 27.3 F1) and a version utilising our prior knowledge of each type of question in selecting a context combination strategy does even better. Our proposed models also generally outperform direct prompts against much larger models (BLOOM 175B and StableVicuna 13B) in both few-shot chain-of-thought and standard few-shot settings.

Baird counterexample was proposed by Leemon Baird in 1995, first used to show that the Temporal Difference (TD(0)) algorithm diverges on this example. Since then, it is often used to test and compare off-policy learning algorithms. Gradient TD algorithms solved the divergence issue of TD on Baird counterexample. However, their convergence on this example is still very slow, and the nature of the slowness is not well understood, e.g., see (Sutton and Barto 2018). This note is to understand in particular, why TDC is slow on this example, and provide a debugging analysis to understand this behavior. Our debugging technique can be used to study the convergence behavior of two-time-scale stochastic approximation algorithms. We also provide empirical results of the recent Impression GTD algorithm on this example, showing the convergence is very fast, in fact, in a linear rate. We conclude that Baird counterexample is solved, by an algorithm with the convergence guarantee to the TD solution in general, and a fast convergence rate.

Large language models (LLMs), such as OpenAI's Codex, have demonstrated their potential to generate code from natural language descriptions across a wide range of programming tasks. Several benchmarks have recently emerged to evaluate the ability of LLMs to generate functionally correct code from natural language intent with respect to a set of hidden test cases. This has enabled the research community to identify significant and reproducible advancements in LLM capabilities. However, there is currently a lack of benchmark datasets for assessing the ability of LLMs to generate functionally correct code edits based on natural language descriptions of intended changes. This paper aims to address this gap by motivating the problem NL2Fix of translating natural language descriptions of code changes (namely bug fixes described in Issue reports in repositories) into correct code fixes. To this end, we introduce Defects4J-NL2Fix, a dataset of 283 Java programs from the popular Defects4J dataset augmented with high-level descriptions of bug fixes, and empirically evaluate the performance of several state-of-the-art LLMs for the this task. Results show that these LLMS together are capable of generating plausible fixes for 64.6% of the bugs, and the best LLM-based technique can achieve up to 21.20% top-1 and 35.68% top-5 accuracy on this benchmark.

Hey Data Scientists, AI and Machine Learning Engineers, and Data Analysts, If we look around, we will find that AI and Data Science are the fastest growing fields in the world where working on data has become very important, and data has become like oil. Hence we see that everything has become data, and the data may differ on the purpose of the problem we have the type of data since there is numerical data, and the data that can be textual and images describing something specific. To put things into perspective, if we look at data scientists and machine learning engineers, first of all, there are many tools for how to work with data and how to manage that data. One of the most famous of these libraries is the open-source Pandas library. Because in most of the libraries that were used in the beginning to work on data, there are many of these types, and here we will touch on an explanation of what is used a lot of times, and I hope that you have already used the same library or have already touched on it before.

Deploying deep learning models on various devices has become an important topic. The wave of hardware specialization brings a diverse set of acceleration primitives for multi-dimensional tensor computations. These new acceleration primitives, along with the emerging machine learning models, bring tremendous engineering challenges. In this paper, we present TensorIR, a compiler abstraction for optimizing programs with these tensor computation primitives. TensorIR generalizes the loop nest representation used in existing machine learning compilers to bring tensor computation as the first-class citizen. Finally, we build an end-to-end framework on top of our abstraction to automatically optimize deep learning models for given tensor computation primitives. Experimental results show that TensorIR compilation automatically uses the tensor computation primitives for given hardware backends and delivers performance that is competitive to state-of-art hand-optimized systems across platforms.

Boosting the runtime performance of deep neural networks (DNNs) is critical due to their wide adoption in real-world tasks. Existing approaches to optimizing the tensor algebra expression of a DNN only consider expressions representable by a fixed set of predefined operators, missing possible optimization opportunities between general expressions. We propose OLLIE, the first derivation-based tensor program optimizer. OLLIE optimizes tensor programs by leveraging transformations between general tensor algebra expressions, enabling a significantly larger expression search space that includes those supported by prior work as special cases. OLLIE uses a hybrid derivation-based optimizer that effectively combines explorative and guided derivations to quickly discover highly optimized expressions. Evaluation on seven DNNs shows that OLLIE can outperform existing optimizers by up to 2.73$\times$ (1.46$\times$ on average) on an A100 GPU and up to 2.68$\times$ (1.51$\times$) on a V100 GPU, respectively.

There are two big players in elixir's XML parsing ecosystem: I want to read a huge XML file that has some elements very repeated, and want to produce some kind of "iterator" from it. I'd like to produce some iterator that, when iterated, produces this: Saxy is incredibly fast and performant, but it's based on the concept that, as you read the XML file, you "fill" some state object (with whatever you want, and the amount you want, but, nevertheless, you fill it). In this scenario, I could "fill" the state with the list of items. That, of course, is a lot less memory than it would take to hold the entire XML structure in memory. But still it establishes a relationship between the size of the XML file and the size of the stored in-memory list, which I don't like because that means that if I use a big enough file, I can consume more memory than I'm allowed to. SweetXml provides some function called stream_tags and when you see what it does, it seems that it hits the spot!!! because it says it's just what I need: parse an xml and, as it finds certain tags, stream the SweetXml representation of them, and it doesn't build into memory any structure representing xml.