arXiv subjects

Yue Guan

Publications and source records attributed to Yue Guan.

At least 19 recordsLinked to original sources

arXiv2026

Qubrio: High-Performance Quantum Compilation via Multi-Agent LLM Collaboration

Large Language Models (LLMs) offer an adaptable alternative to traditional quantum compilation heuristics, which bottleneck progress by demanding costly manual redesigns whenever hardware evolves. However, naive single-pass LLM approaches fail under the unique challenges introduced by quantum compilation. We introduce Qubrio, a practical agentic framework that significantly reduces heuristic redesigns through a three-level decomposition. By (1) partitioning programs into sequential operation stages, (2) deploying specialized agents for placement, routing and optimization, and (3) using disaggregated feedback for precise error correction, our system reliably navigates complex physical constraints. Beyond serving as a direct compiler, our LLM framework also uncovers novel strategies that facilitate convoy-style shuttling, substantially enhancing hardware concurrency without sacrificing fidelity. We further integrate these strategies into the previous state-of-the-art (SOTA) compiler, recovering a significant fraction of the LLM's performance advantages. On realistic workloads, our compiler achieves significant improvements in hardware runtime and program fidelity over the SOTA baseline PowerMove, seamlessly adapting to new hardware capabilities. Qubrio features an open user interface for practical use, and its code is publicly available at https://github.com/crosaa/Qubrio.

quant-ph↗

arXiv2026

Understanding GPU Megakernels: Why Residency Can Mislead

Megakernels let one persistent GPU program prepare dependent operators early and execute ready tasks together. We study the benefits and costs of these capabilities by reconstructing two LLM megakernels, ThunderKittens (TK) and VDCores, as separate kernels on H100 using their original operator code. Our results show that CTA residency can misrepresent opportunities for useful overlap in both directions. By overlapping startup and operand loading with programmatic dependent launch (PDL), the reconstructions reduce decode-step latency by 5.7% in TK and achieve comparable performance in VDCores when both executions enforce the required memory ordering. Under whole-operator dependencies, TK's persistent execution still gains more from prefetch, but runtime and completion-signal ordering costs outweigh this advantage. Both startup overlap and prefetch depend on resource availability. Persistent CTAs can reuse storage before retiring, whereas separate successors must acquire their full CTA footprints before initializing or loading operands. This admission constraint in both reconstructions motivates finer resource sharing across kernels. Beyond early preparation, joint execution requires ready work and spare capacity in the bottleneck resource. Reserving SMs for communication can add GEMM waves that erase overlap gains, while filling idle SMs offers little benefit once memory bandwidth is saturated. These findings clarify benefits and costs of megakernels and motivate GPU support for earlier resource reuse across kernels.

cs.DC↗

arXiv2026

HiState: Hierarchical Prefix Cache Management for Hybrid LLM Serving in Agentic Workloads

Hybrid large language models combine full-attention and recurrent linear layers to reduce inference costs. Prefix caching can further reduce redundant computation across requests, but a recurrent checkpoint cannot recover an earlier state corresponding to a shorter prefix. Existing hybrid prefix caching systems retain checkpoints at selected boundaries to support common reuse patterns in conventional conversations. However, agent workloads modify and revisit earlier contexts, exposing reusable prefixes whose checkpoints were never saved or have already been evicted. A straightforward approach is to retain more checkpoints to reduce recomputation, but their cumulative footprint can displace reusable prefixes from other sessions and cause additional cache misses. To address these problems, we present HiState, a prefix cache management system for hybrid models serving agent workloads. Our key observation is that prefix reuse accesses all matching key-value (KV) entries but only one recurrent checkpoint, regardless of how many checkpoints are retained. This asymmetry allows HiState to retain historical checkpoints on SSD while prioritizing fast memory for KV entries: each hit retrieves only one checkpoint whose size is independent of context length. Within this hierarchy, we propose adaptive interval control to balance checkpoint storage against recomputation, and unified eviction to coordinate checkpoint sparsification with reclamation of stale trajectories. We implement HiState on top of vLLM and evaluate it on two public coding-agent trace datasets and controlled microbenchmarks. On real agent traces, HiState achieves up to 5.73x and 5.44x speedups in p99 TTFT over vLLM-Marconi and SGLang-HiCache, respectively.

cs.DC↗

arXiv2026

Asymmetric-Information Resource Allocation Games: An LP Approach to Purposeful Deception

In this work, we introduce the Deceptive Resource Allocation Game (DRAG), which studies purposeful deception within a Bayesian game framework. In DRAG, a Defender allocates resources across the true asset and several decoys to influence an Attacker's beliefs and actions, with the goal of diverting the Attacker away from the true asset. We seek to characterize purposeful deception, whereby the Defender deceives only when doing so improves its performance. To this end, we solve for the Perfect Bayesian Nash Equilibrium (PBNE) of the corresponding game. We show that, despite the coupled belief-policy interdependence, the problem admits an efficient, non-iterative linear programming formulation. Numerical results demonstrate that the resulting policies naturally balance effective allocation and belief manipulation, giving rise to purposeful and emergent deceptive behaviors.

cs.GT↗

arXiv2026

Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions

While multi-agent reinforcement learning (MARL) has been proven effective across both collaborative and competitive tasks, existing algorithms often struggle to scale to large populations of agents. Recent advancements in mean-field (MF) theory provide scalable solutions by approximating population interactions as a continuum, yet most existing frameworks focus exclusively on either fully cooperative or purely competitive settings. To bridge this gap, we introduce MF-MAPPO, a mean-field extension of PPO designed for zero-sum team games that integrate intra-team cooperation with inter-team competition. MF-MAPPO employs a shared actor and a minimally informed critic per team and is trained directly on finite-population simulators, thereby enabling deployment to realistic scenarios with thousands of agents. We further show that MF-MAPPO naturally extends to partially observable settings through a simple gradient-regularized training scheme. Our evaluation utilizes large-scale benchmark scenarios using our own testing simulation platform for MF team games (MFEnv), including offense-defense battlefield tasks as well as variants of population-based rock-paper-scissors games that admit analytical solutions, for benchmarking. Across these benchmarks, MF-MAPPO outperforms existing methods and exhibits complex, heterogeneous behaviors, demonstrating the effectiveness of combining mean-field theory and MARL techniques at scale.

cs.MA↗

arXiv2026

Feedback Dominance Analysis for Pursuit-Evasion Games on Graphs

This work identifies the dominance regions for discrete, simultaneous-move pursuit-evasion games on graphs. Existing geometric approaches provide efficient characterizations of winning regions, but typically provide only sufficient conditions and rely on open-loop strategies. To address these challenges, we develop a set-based dynamic programming approach to characterize the pursuer's winning and losing regions, providing necessary and sufficient winning conditions under worst-case behavior. The reachability analysis admits a set-chasing interpretation, allowing translation of dominance sets to feedback strategies that adapt to the players' positions in real time. For states where neither player can guarantee victory, we introduce an instantaneous matrix-game formulation and establish upper and lower bounds on the pursuer's winning probability. Simulation results validate the correctness of the dominance-region characterization and the proposed bounds.

cs.GT↗

arXiv2026

Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Measurements across four domains and four open-weight targets, plus floor estimates on a frontier API target, yield three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for $43$--$64\%$ of DFlash rejection and $85$--$92\%$ of DSpark's oracle-conditioned rejection. Guided by this separation of short-range conditioning from proposal quality, we replace a context-independent predecessor correction with a prefix-attention head that reads committed context conditional on the predecessor. With supporting backbone components, the resulting Qwen3-4B drafter improves mean serving accepted length by $3.93\%$ over the released DSpark checkpoint across nine tasks, without increasing the conditioning order. Code and data: https://github.com/tie-pilot-qxw/specfloor; drafter checkpoints: https://huggingface.co/TIE-Pilot/dspark-attnconv-block7-qwen3-4b.

cs.LG↗

arXiv2026

PDO-Split: A Real-Time Solver for Constrained Potential-Dominant Games

We present Potential-Dominant Operator Splitting (PDO-Split), a real-time generalized Nash equilibrium solver for constrained dynamic multi-agent problems with potential-dominant structure. PDO-Split targets the computational bottleneck in game-theoretic model predictive control, where repeatedly solving the equilibrium KKT system becomes costly as the number of agents increases. We introduce a class of gamma-potential-dominant games, in which the potential (or cooperative) structure dominates the competitive interactions between the agents. We show that this structure allows PDO-Split to use the potential component as a preconditioner while incorporating the competitive component through iterative refinement. We establish convergence guarantees and exploit the symmetry of the potential component through a reusable LDL^T factorization to accelerate the linear solvers. We evaluate PDO-Split across several practical multi-agent planning problems, including eight-car racing and six-vehicle ramp merging, achieving substantially improved runtime and convergence rate over existing DDP-based and Newton-based methods, especially with a larger number of agents. The algorithm is also experimentally validated on miniature autonomous race car platforms, demonstrating the approach's real-time capability.

cs.GT↗

arXiv2026

Argus: Orchestrating Cross-Layer GPU Performance Measurements around Semantic Regions

GPU developers and automated optimizers need performance evidence for semantic code regions--such as neural-network operator implementations and pipeline stages--but this evidence is fragmented across profiling tools. Answering a region-level question can require manually constructing probes and program variants, isolating interfering measurements, and mapping evidence to regions and execution contexts. We present Argus, a region-centric measurement planner and runtime that automates this workflow. Clients identify regions with boundary markers and select signals and execution scopes. Argus preserves region identity across compilation, execution, and measurement variants, constructs interference-aware multi-run plans, and orchestrates transformations and profiling across backends. It joins compiler-, hardware-, and system-level evidence using region identity and dynamic execution context, producing reports that record measurement origins and attribution ambiguity. We evaluate Argus across agentic kernel optimization, persistent megakernel optimization, and cross-level PGO. Across 44 persistent-GEMM and attention configurations, Argus improves 39/44 cases and raises AlphaEvolve's geometric-mean speedup from 5.4% to 8.9%. On a persistent TinyLlama-1.1B decode megakernel, an optimization agent reaches 1.65 ms/token with Argus versus 4.92 ms/token without it, producing a kernel $2.1\times$ faster than PyTorch with CUDA Graphs. Finally, Argus-guided cross-level PGO improves compute--communication overlap, increasing throughput by 7% on average across five multi-GPU settings.

cs.DC↗

arXiv2026

Offline Nash Solvers Meet Online Tree Search in Multi-Agent Games on Graphs

Computing Nash equilibrium policies in multi-agent Pursuit-Evasion games (PEG) is challenging due to the exponential growth of the joint state and action spaces with the number of agents. Existing approaches either rely on offline equilibrium approximations, which may lack adaptability during execution, or online planning methods, which suffer from large branching factors. In this work, we propose Primitive-Guided Tree Search (PGTS), a hybrid framework that integrates offline exact Nash equilibrium computation with online tree search: PGTS first solves a collection of smaller, tractable sub-games offline; at deployment, PGTS performs online tree search at each time step, using the optimal sub-game policies and value functions to guide tree expansion and estimate leaf-node values. Extensive experiments on varied graph topologies, including real-world networks, demonstrate that PGTS significantly outperforms state-of-the-art learning and heuristic baselines, while maintaining robust performance against adversaries.

cs.GT↗

arXiv2026

Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap

Communication has become a first-order bottleneck in large-scale GPU workloads, and existing distributed compilers address it mainly by overlapping whole compute and communication kernels at the stream level. This coarse granularity incurs extra kernel launches, forces device-wide synchronizations at kernel boundaries, and leaves substantial slack when the slowest tile or kernel stretches the communication tail. We present Syncopate, a compiler and runtime that enables automatic fine-grained overlap inside a single fused kernel. Syncopate introduces a communication chunk abstraction that decouples communication granularity from kernel structure and backend mechanisms, allowing chunk-level plans to be ported from existing distributed compilers, written directly by users, or instantiated from reusable templates. Given a local Triton kernel and a chunk schedule, Syncopate performs transformations to align computation with chunk availability. Implemented as a source-to-source compiler on Triton, Syncopate delivers an average end-to-end speedup of 1.3$\times$ and up to 4.7$\times$ on multi-GPU workloads. Our code is open-sourced at https://github.com/tie-pilot-qxw/syncopate.

cs.DC↗

arXiv2026

SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering

LLM-based agents execute multi-turn workflows with continuously growing contexts, where LLM calls are interleaved with tool invocations and environment feedback. To maintain model quality, modern agent frameworks rely on context engineering strategies such as offloading, reduction, and isolation to control the context length. However, these strategies introduce significant context transformation overhead: each transformation invalidates existing KV caches and triggers re-prefill, leading to increased time-to-first-token (TTFT). In this paper, we identify that context transformations are segment-decomposable, where the transformation of a prefix is independent of future tokens. This property enables transformations to be executed ahead of time. Based on this insight, we propose a lookahead programming model that allows agent frameworks to express context transformations as asynchronous operations without modifying their execution logic. The runtime proactively executes these transformations and prepares transformed KV caches in advance, enabling direct context replacement without blocking. We further design a lookahead-aware scheduler in LLM serving systems to support these asynchronous requests alongside latency-critical workloads with controlled interference. We implement our approach to support representative context engineering strategies and integrate it into existing agent frameworks and LLM serving systems. Experiments show that our approach effectively eliminates transformation overhead and reduces TTFT by up to 11.9x.

cs.DC↗

arXiv2026

Performance-Driven Environment Abstraction with Multi-Timescale Learning

We study performance-driven environment abstraction for decision-making in large Markov decision processes. Rather than preserving geometric or topological structure, we seek abstractions that directly optimize decision quality. We model abstraction as a controlled approximation obtained by aggregating the state space and enforcing a shared action distribution within each aggregated state. For a fixed partition, we establish a performance guarantee that separates value-function approximation error from the loss introduced by action sharing. Guided by this analysis, we develop a multi-timescale reinforcement learning framework that jointly adapts the policy and a tree-structured environment abstraction. The resulting algorithm refines and coarsens regions of the state space based on Q-value discrepancies, balancing performance against abstraction size and complexity. Empirical results demonstrate substantial state compression, improved sample efficiency, and faster replanning compared to actor-critic baselines.

cs.LG↗

arXiv2026

A container theorem for general digraphs with forbidden subdigraphs

In a seminal work, Kühn, Osthus, Townsend, and Zhao used the hypergraph container method to determine the typical structure of oriented graphs and digraphs avoiding a fixed tournament or cycle. Their main tool, a container theorem for oriented graphs, does not directly extend to all digraphs due to the existence of counterexamples such as the double triangle $DK_3$. In this paper we prove a container theorem for general digraphs under a natural sparsity condition. For the edge-weight parameter $a=2$, this condition permits digraphs with $2$-cycles (density at most $1$) but excludes denser obstructions like $DK_3$; for larger $a$ it allows digraphs with a controlled density of $2$-cycles. As applications, we obtain asymptotic counting results for $H$-free digraphs and describe the typical structure of digraphs avoiding a fixed digraph $H$ satisfying our condition. Our results unify and extend several previous results in the area.

math.CO↗

arXiv2026

FlashCP: Load-Balanced Communication-Efficient Context Parallelism for LLM Training

Context parallelism (CP) is essential for training large-scale, long-context language models, as it partitions sequences to reduce memory overhead. However, existing CP methods suffer from workload imbalance, inefficient kernels, and redundant communication due to static sequence sharding and key-value (KV) tensor communication. We present FlashCP, a load-balanced and communication-efficient framework for CP training. FlashCP introduces a sharding-aware communication mechanism to eliminate redundant KV communication and proposes a novel Whole-Doc sharding strategy that maximizes communication savings while maintaining balanced workloads. To efficiently combine Whole-Doc and Per-Doc sharding, FlashCP further designs a heuristic algorithm to search for near-optimal sharding plans. Extensive experiments show that FlashCP achieves up to 1.63x speedup over state-of-the-art CP frameworks across diverse datasets.

cs.DC↗

arXiv2026

The typical structure of oriented graphs and digraphs with forbidden blow-up of transitive tournaments

For integers $r\ge 2$, $t\ge 1$ and a real number $a\in(3/2,2]$, we study the typical structure of oriented graphs and digraphs that do not contain a blow-up $T_{r+1}^t$ of a transitive tournament. We prove that almost every $T_{r+1}^t$-free oriented graph on n vertices admits an r-partition $V_1\cup\cdots\cup V_r$ such that each induced subgraph $G[V_i]$ is $T_2^t$-free, and the same holds for almost every $T_{r+1}^t$-free digraph.Consequently, the number $f(n,T_{r+1}^t)$ of labelled $T_{r+1}^t$-free oriented graphs satisfies $f(n,T_{r+1}^t)=|\mathcal{P}_{n,r,t}|(1+o(1))$, where $\mathcal{P}_{n,r,t}$ is the family of oriented graphs admitting such an r-partition with each part $T_2^t$-free; an analogous statement holds for digraphs.When $t=1$ this recovers the result of K"uhn, Osthus, Townsend and Zhao (2017) that almost all $T_{r+1}$-free oriented graphs (resp. digraphs) are r-partite, thereby confirming a generalised form of Cherlin's conjecture. Our proof combines the hypergraph container method, a weighted Erdős-Stone theorem, and a stability analysis for near-extremal $T_{r+1}^t$-free digraphs.

math.CO↗

arXiv2026

Linear Programming Approach to Deceptive Path Planning Game with Goal Selection

In adversarial settings, a mobile agent may strategically plan its motion to influence an opponent's inference about its intended goal. We study deceptive path planning in a scenario where a mobile agent aims to reach a privately selected goal while an adversarial observer allocates limited defensive resources based on the observed trajectory. Unlike classical path-planning and goal-recognition approaches that model observers as passive inference process, our game-theoretic formulation models them as strategic decision-makers. For the resulting dynamic asymmetric-information game, we develop an efficient solution method that combines a linear programming formulation with the Double Oracle algorithm. To evaluate performance, we introduce metrics that quantify both the risk and the effectiveness of deception and provide illustrative numerical examples.

eess.SY↗

arXiv2026

TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments

Modern GPUs increasingly rely on specialized hardware units and asynchronous coordination mechanisms, so performance depends on orchestrating data movement, tensor-core computation, and synchronization rather than exposing more thread-level parallelism. This creates a programming-model tension: if too much execution structure is hidden, the compiler must catch up to new hardware mechanisms; if too much is exposed, the burden of orchestration falls back onto the programmer. We present TLX (Triton Low-level Language Extensions), built around MIMW (Multi-Instruction, Multi-Warp), which expresses orchestration at warp-group granularity while preserving Triton's productive blocked programming model for regular computation. TLX realizes this idea as an embedded extension to Triton, exposing explicit interfaces for multi-warp execution, local-memory orchestration, asynchronous operations, and cluster-aware control. Our evaluation shows that TLX supports substantial customization with limited development effort while remaining competitive with state-of-the-art implementations. TLX-authored kernels have been deployed in large-scale training and inference production systems. Our code is open sourced at https://github.com/facebookexperimental/triton.

cs.AR↗