arXiv subjects

Ales Kubicek

Publications and source records attributed to Ales Kubicek.

13 recordsLinked to original sources

arXiv2026

Performance Foundations of Parallel & Distributed Reasoning Language Models

Reinforcement Learning with Verifiable Rewards (RLVR) and other RL-style post-training paradigms have been used for aligning large language models (LLMs) with reasoning standards. The resulting recent Reasoning Language Models (RLMs) such as DeepSeek-R1, o3, and Kimi k1.5 show that such RL-style post-training ("RL-for-LLMs") can substantially improve chain-of-thought reasoning, long-horizon planning, and self-correction. However, the computational footprint of these systems is massive: state-of-the-art RLM training requires millions of GPU-hours and tightly coupled multi-model pipelines that stress modern hardware far beyond classical supervised LLM training. This makes RLM training as much a parallel and distributed systems problem as an algorithmic one. In this work, to facilitate developing RLMs that are simultaneously high-performance, scalable, and cost-effective, we first systematize the RL-for-LLM paradigm and provide a compute-centric analysis of prominent post-training algorithmic frameworks: Proximal Policy Optimization (PPO), Group Relative Policy Optimization (GRPO), as well as their variants. Second, we develop a taxonomy of intra- and inter-model parallelism strategies for RL-for-LLMs, covering both traditional techniques (data, tensor, pipeline, sequence, context, and expert parallelism) as well as novel forms of parallelism and optimization techniques for multi-model RLM training, for example disaggregated placement, stage fusion, hybrid parallelism, and asynchronous execution. We harness the work-depth model of parallel computing to make our taxonomy and its insights rigorous and portable. Finally, we analyze existing RLM frameworks and we distill practical guidelines and outline open research directions for building scalable, fast, and cost-effective RLMs.

cs.LG↗

arXiv2026

DiG-bench: Discovery in Games

Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI benchmark landscape, with few benchmarks directly probing the capacity for discovering new knowledge with experimentation in controlled environments where the objective is unknown. To address this gap, we release a new benchmark: DiG-bench (Discovery in Games). DiG-bench consists of a set of 70 independent games. Each game is encoded as a short string and has unique transformation rules that must be discovered through interaction and experimentation. The levels of the game present a series of challenges to test whether the rules have been discovered, where the win conditions for each level are also unknown. We provide games at seven tiers of difficulty for AI agents. The lowest tier is routinely solvable by multiple models, while the highest tier challenges the best models in agentic harnesses. All 70 games were solved by at least one human on first attempt. A subset of 21 games is released publicly, and the remainder is held private for secure evaluation.

cs.AI↗

arXiv2026

Demystifying Chains, Trees, and Graphs of Thoughts

The field of natural language processing (NLP) has witnessed significant progress in recent years, with a notable focus on improving large language models' (LLM) performance through innovative prompting techniques. Among these, prompt engineering coupled with structures has emerged as a promising paradigm, with designs such as Chain-of-Thought, Tree of Thoughts, or Graph of Thoughts, in which the overall LLM reasoning is guided by a structure such as a graph. As illustrated with numerous examples, this paradigm significantly enhances the LLM's capability to solve numerous tasks, ranging from logical or mathematical reasoning to planning or creative writing. To facilitate the understanding of this growing field and pave the way for future developments, we devise a general blueprint for effective and efficient LLM reasoning schemes. For this, we conduct an in-depth analysis of the prompt execution pipeline, clarifying and clearly defining different concepts. We then build the first taxonomy of structure-enhanced LLM reasoning schemes. We focus on identifying fundamental classes of harnessed structures, and we analyze the representations of these structures, algorithms executed with these structures, and many others. We refer to these structures as reasoning topologies, because their representation becomes to a degree spatial, as they are contained within the LLM context. Our study compares existing prompting schemes using the proposed taxonomy, discussing how certain design choices lead to different patterns in performance and cost. We also outline theoretical underpinnings, relationships between prompting and other parts of the LLM ecosystem such as knowledge bases, and the associated research challenges. Our work will help to advance future prompt engineering techniques.

cs.CL↗

arXiv2026

Multi-Head RAG: Solving Multi-Aspect Problems with LLMs

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by retrieving supporting documents into the prompt, but existing methods do not explicitly target queries that require fetching multiple documents with substantially different content. Such multi-aspect queries are challenging because relevant documents can be far apart in embedding space, making joint retrieval difficult. We introduce Multi-Head RAG (MRAG), which addresses this gap with a simple yet powerful idea: using Transformer multi-head attention activations rather than the standard decoder-layer embedding, as retrieval keys. It leverages the observation that different heads capture different semantic aspects. This yields multi-aspect embeddings for both documents and queries, improving retrieval accuracy on complex queries. We show MRAG's design advantages over 18 RAG baselines, up to 20% higher retrieval success ratios for real-world use cases, and improved downstream LLM generation. MRAG integrates seamlessly with existing RAG frameworks and benchmarks.

cs.CL↗

arXiv2026

Spritz: Path-Aware Load Balancing in Low-Diameter Networks

Low-diameter topologies such as Dragonfly and Slim Fly are increasingly adopted in HPC and datacenter networks, yet existing load balancing techniques either rely on proprietary in-network mechanisms or fail to utilize the full path diversity of these topologies. We introduce Spritz, a flexible sender-based load balancing framework that shifts adaptive topology-aware routing to the endpoints using only standard Ethernet features. We propose two algorithms, Spritz-Scout and Spritz-Spray that, respectively, explore and adaptively cache efficient paths using ECN, packet trimming, and timeout feedback. Through simulation on Dragonfly and Slim Fly topologies with over 1000 endpoints, Spritz outperforms ECMP, UGAL-L, and prior sender-based approaches by up to 1.8x in flow completion time under AI training and datacenter workloads, while offering robust failover with performance improvements of up to 25.4x under link failures, all without additional hardware support. Spritz enables datacenter-scale, commodity Ethernet networks to efficiently leverage low-diameter topologies, offering unified routing and load balancing for the Ultra Ethernet era.

cs.NI↗

arXiv2025

Affordable AI Assistants with Knowledge Graph of Thoughts

Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains. However, current state-of-the-art LLM-driven agents face significant challenges, including high operational costs and limited success rates on complex benchmarks like GAIA. To address these issues, we propose Knowledge Graph of Thoughts (KGoT), an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs). KGoT extracts and structures task-relevant knowledge into a dynamic KG representation, iteratively enhanced through external tools such as math solvers, web crawlers, and Python scripts. Such structured representation of task-relevant knowledge enables low-cost models to solve complex tasks effectively while also minimizing bias and noise. For example, KGoT achieves a 29% improvement in task success rates on the GAIA benchmark compared to Hugging Face Agents with GPT-4o mini. Moreover, harnessing a smaller model dramatically reduces operational costs by over 36x compared to GPT-4o. Improvements for other models (e.g., Qwen2.5-32B and Deepseek-R1-70B) and benchmarks (e.g., SimpleQA) are similar. KGoT offers a scalable, affordable, versatile, and high-performing solution for AI assistants.

cs.AI↗

arXiv2025

CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks

Large Language Models (LLMs) are transforming a wide range of domains, yet verifying their outputs remains a significant challenge, especially for complex open-ended tasks such as consolidation, summarization, and knowledge extraction. To address this, we introduce CheckEmbed (CE): a simple, scalable, and accurate verification method. CE reduces each LLM answer to a single embedding vector using powerful modern embedding LLM models like SFR-Embedding-Mistral. Prior methods such as BERTScore and SelfCheckGPT relied on weaker encoders like BERT, forcing them to operate at token or sentence granularity. In contrast, CE performs fast, semantically rich comparisons directly at the whole-answer level, overcoming key limitations in both accuracy and scalability. We conduct a comprehensive design and time complexity analysis across 13 verification baselines, including classical text scorers (e.g., BLEU), stability-based methods (e.g., SelfCheckGPT), and generative evaluators (e.g., LLM-as-a-Judge), which highlights the effectiveness, efficiency, versatility, and simplicity of CE. Empirical results show that CE reliably detects hallucinations in both closed and open-ended tasks. We further present evidence that CE generalizes beyond text to other modalities such as vision, establishing it as a practical and versatile verification framework.

cs.CL↗

arXiv2025

CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training

Training large language models (LLMs) now requires resources that exceed a single datacenter, making cross-datacenter strategies increasingly crucial. We present CrossPipe, a framework designed to optimize model training across geographically distributed datacenters by explicitly modeling and mitigating the impact of network latency and limited bandwidth. It enables unified analysis and optimization incorporating both pipeline parallelism (PP) and opportunities for overlapping data parallelism (DP) communication. CrossPipe generates optimized pipeline schedules using either solver-based optimal or fast near-optimal greedy algorithms, built upon a flexible execution engine that separates scheduling logic from communication details. Our evaluation shows that CrossPipe reduces training time by up to 33.6\% compared to traditional pipeline schedules under identical memory constraints. When memory constraints are relaxed, CrossPipe maintains strong performance despite communication delays, approaching the efficiency of idealized schedules without delays. CrossPipe offers improved scalability and resource utilization, particularly in environments with high network latency or limited bandwidth.

cs.DC↗

arXiv2025

Reasoning Language Models: A Blueprint

Reasoning language models (RLMs), also known as Large Reasoning Models (LRMs), such as OpenAI's o1 and o3, DeepSeek-R1, and Alibaba's QwQ, have redefined AI's problem-solving capabilities by extending LLMs with advanced reasoning mechanisms. Yet, their high costs, proprietary nature, and complex architectures - uniquely combining reinforcement learning (RL), search heuristics, and LLMs - present accessibility and scalability challenges. To address these, we propose a comprehensive blueprint that organizes RLM components into a modular framework, based on a survey and analysis of all RLM works. This blueprint incorporates diverse reasoning structures (chains, trees, graphs, and nested forms), reasoning strategies (e.g., Monte Carlo Tree Search, Beam Search), RL concepts (policy, value models and others), supervision schemes (Outcome-Based and Process-Based Supervision), and other related concepts (e.g., Test-Time Compute, Retrieval-Augmented Generation, agent tools). We also provide detailed mathematical formulations and algorithmic specifications to simplify RLM implementation. By showing how schemes like LLaMA-Berry, QwQ, Journey Learning, and Graph of Thoughts fit as special cases, we demonstrate the blueprint's versatility and unifying potential. To illustrate its utility, we introduce x1, a modular implementation for rapid RLM prototyping and experimentation. Using x1 and a literature review, we provide key insights, such as multi-phase training for policy and value models, and the importance of familiar training distributions. Finally, we discuss scalable RLM cloud deployments and we outline how RLMs can integrate with a broader LLM ecosystem. Our work demystifies RLM construction, democratizes advanced reasoning capabilities, and fosters innovation, aiming to mitigate the gap between "rich AI" and "poor AI" by lowering barriers to RLM design and experimentation.

cs.AI↗

arXiv2025

Edge-Disjoint Spanning Trees on Star-Product Networks

A star-product operation may be used to create large graphs from smaller factor graphs. Network topologies based on star-products demonstrate several advantages including low-diameter, high scalability, modularity and others. Many state-of-the-art diameter-2 and -3 topologies~(Slim Fly, Bundlefly, PolarStar etc.) can be represented as star products. In this paper, we explore constructions of edge-disjoint spanning trees~(EDSTs) in star-product topologies. EDSTs expose multiple parallel disjoint pathways in the network and can be leveraged to accelerate collective communication, enhance fault tolerance and network recovery, and manage congestion. Our EDSTs have provably maximum or near-maximum cardinality which amplifies their benefits. We further analyze their depths and show that for one of our constructions, all trees have order of the depth of the EDSTs of the factor graphs, and for all other constructions, a large subset of the trees have that depth.

cs.NI↗

arXiv2024

A High-Performance Design, Implementation, Deployment, and Evaluation of The Slim Fly Network

Novel low-diameter network topologies such as Slim Fly (SF) offer significant cost and power advantages over the established Fat Tree, Clos, or Dragonfly. To spearhead the adoption of low-diameter networks, we design, implement, deploy, and evaluate the first real-world SF installation. We focus on deployment, management, and operational aspects of our test cluster with 200 servers and carefully analyze performance. We demonstrate techniques for simple cabling and cabling validation as well as a novel high-performance routing architecture for InfiniBand-based low-diameter topologies. Our real-world benchmarks show SF's strong performance for many modern workloads such as deep neural network training, graph analytics, or linear algebra kernels. SF outperforms non-blocking Fat Trees in scalability while offering comparable or better performance and lower cost for large network sizes. Our work can facilitate deploying SF while the associated (open-source) routing architecture is fully portable and applicable to accelerate any low-diameter interconnect.

cs.NI↗

arXiv2024

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks.

cs.CL↗

arXiv2023

TornadoQSim: An Open-source High-Performance and Modular Quantum Circuit Simulation Framework

In this article, we present TornadoQSim, an open-source quantum circuit simulation framework implemented in Java. The proposed framework has been designed to be modular and easily expandable for accommodating different user-defined simulation backends, such as the unitary matrix simulation technique. Furthermore, TornadoQSim features the ability to interchange simulation backends that can simulate arbitrary quantum circuits. Another novel aspect of TornadoQSim over other quantum simulators is the transparent hardware acceleration of the simulation backends on heterogeneous devices. TornadoQSim employs TornadoVM to automatically compile parts of the simulation backends onto heterogeneous hardware, thereby addressing the fragmentation in development due to the low-level heterogeneous programming models. The evaluation of TornadoQSim has shown that the transparent utilization of GPU hardware can result in up to 506.5$x$ performance speedup when compared to the vanilla Java code for a fully entangled quantum circuit of 11 qubits. Other evaluated quantum algorithms have been the Deutsch-Jozsa algorithm (493.10$x$ speedup for a 11-qubit circuit) and the quantum Fourier transform algorithm (518.12$x$ speedup for a 11-qubit circuit). Finally, the best TornadoQSim implementation of unitary matrix has been evaluated against a semantically equivalent simulation via Qiskit. The comparative evaluation has shown that the simulation with TornadoQSim is faster for small circuits, while for large circuits Qiskit outperforms TornadoQSim by an order of magnitude.

quant-ph↗