arXiv subjects

Yue Guan

Publications and source records attributed to Yue Guan.

At least 37 records · Page 2Linked to original sources

arXiv2026

Dynamic Adversarial Resource Allocation: the dDAB Game

This work introduces the dynamic Defender-Attacker Blotto (dDAB) game, extending the classical static Blotto game to a dynamic resource allocation setting over graphs. In the dDAB game, a defender is required to maintain numerical superiority against attacker resources across a set of key nodes in a connected graph. The engagement unfolds as a discrete-time game, where each player reallocates its resources in turn, with resources allowed to move at most one hop per time step. The primary goal is to determine the necessary and sufficient amount of defender resources required to guarantee sustained defense, along with the corresponding strategies. To address the central challenge arising from graph-constrained resource reallocation, we conduct a reachability analysis, starting with simplified settings where attacker resources act as a single cohesive group. We then extend the framework to allow attacker resources to split and merge arbitrarily, and construct defender strategies using superposition principles. A set-based dynamic programming algorithm is developed to compute the optimal strategies, as well as the minimum amount of defender resources to ensure successful defense. The effectiveness of our approach is demonstrated through numerical simulations and hardware experiments on the Georgia Tech Robotarium platform.

cs.MA↗

arXiv2026

Strategic Concealment of Environment Representations in Competitive Games

This paper investigates the strategic concealment of environment representations used by players in competitive games. We consider a defense scenario in which one player (the Defender) seeks to infer and exploit the representation used by the other player (the Attacker). The interaction between the two players is modeled as a Bayesian game: the Defender infers the Attacker's representation from its trajectory and places barriers to obstruct the Attacker's path towards its goal, while the Attacker obfuscates its representation type to mislead the Defender. We solve for the Perfect Bayesian Nash Equilibrium via a bilinear program that integrates Bayesian inference, strategic planning, and belief manipulation. Simulations show that purposeful concealment naturally emerges: the Attacker randomizes its trajectory to manipulate the Defender's belief, inducing suboptimal barrier selections and thereby gaining a strategic advantage.

cs.MA↗

arXiv2026

Pancake: Hierarchical Memory System for Multi-Agent LLM Serving

In this work, we identify and address the core challenges of agentic memory management in LLM serving, where large-scale storage, frequent updates, and multiple coexisting agents jointly introduce complex and high-cost approximate nearest neighbor (ANN) searching problems. We present Pancake, a multi-tier agentic memory system that unifies three key techniques: (i) multi-level index caching for single agents, (ii) coordinated index management across multiple agents, and (iii) collaborative GPU-CPU acceleration. Pancake exposes easy-to-use interface that can be integrated into memory-based agents like Mem-GPT, and is compatible with agentic frameworks such as LangChain and LlamaIndex. Experiments on realistic agent workloads show that Pancake substantially outperforms existing frameworks, achieving more than 4.29x end-to-end throughput improvement.

cs.MA↗

arXiv2026

Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions and Online Opponent Modeling

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

Robust Mean-Field Games with Risk Aversion and Bounded Rationality

Recent advances in mean-field game literature enable the reduction of large-scale multi-agent problems to tractable interactions between a representative agent and a population distribution. However, existing approaches typically assume a fixed initial population distribution and fully rational agents, limiting robustness under distributional uncertainty and cognitive constraints. We address these limitations by introducing risk aversion with respect to the initial population distribution and by incorporating bounded rationality to model deviations from fully rational decision-making agents. The combination of these two elements yields a new and more general equilibrium concept, which we term the mean-field risk-averse quantal response equilibrium (MF-RQE). We establish existence results and prove convergence of fixed-point iteration and fictitious play to MF-RQE. Building on these insights, we develop a scalable reinforcement learning algorithm for scenarios with large state-action spaces. Numerical experiments demonstrate that MF-RQE policies achieve improved robustness relative to classical mean-field approaches that optimize expected cumulative rewards under a fixed initial distribution and are restricted to entropy-based regularizers.

cs.MA↗

arXiv2026

ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management

LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-resident states, including models, prefix caches, and adapters, which quickly exhaust device memory as the agent count grows. We identify two key properties of these workloads: sparse agent activation and an estimable agent invocation order. Based on an analysis of representative workload classes, we introduce invocation distance, a unified abstraction that estimates the relative order in which agents will issue future LLM requests. Leveraging this abstraction, we present ScaleSim, a memory-efficient LLM serving system for large-scale multi-agent simulations. ScaleSim enables proactive prefetching and priority-based eviction, supports diverse agent-specific memory through a modular interface, and achieves up to 1.74x speedup over SGLang on simulation benchmarks.

cs.AI↗

arXiv2025

Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding

Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We present Yggdrasil, a co-designed system that enables latency-optimal speculative decoding through context-aware tree drafting and compiler-friendly execution. Yggdrasil introduces an equal-growth tree structure for static graph compatibility, a latency-aware optimization objective for draft selection, and stage-based scheduling to reduce overhead. Yggdrasil supports unmodified LLMs and achieves up to $3.98\times$ speedup over state-of-the-art baselines across multiple hardware setups.

cs.LG↗

arXiv2025

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows

Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse key-value (KV) tensors corresponding to agents' fixed prompts, thereby avoiding redundant computation across repeated invocations. However, current systems typically evict KV caches using a Least Recently Used (LRU) policy, which fails to anticipate future agent usage and often discards KV caches shortly before their reuse. This leads to frequent cache misses and substantial recomputation or swapping overhead. We present KVFlow, a workflow-aware KV cache management framework tailored for agentic workloads. KVFlow abstracts the agent execution schedule as an Agent Step Graph and assigns each agent a steps-to-execution value that estimates its temporal proximity to future activation. These values guide a fine-grained eviction policy at the KV node level, allowing KVFlow to preserve entries likely to be reused and efficiently manage shared prefixes in tree-structured caches. Moreover, KVFlow introduces a fully overlapped KV prefetching mechanism, which proactively loads required tensors from CPU to GPU in background threads for agents scheduled in the next step, thereby avoiding cache miss stalls during generation. Compared to SGLang with hierarchical radix cache, KVFlow achieves up to 1.83$\times$ speedup for single workflows with large prompts, and up to 2.19$\times$ speedup for scenarios with many concurrent workflows.

cs.DC↗

arXiv2025

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the integration of VQ with various computations. The codebook cache adaptively stores different entries across the GPU's memory hierarchy, including off-chip global memory, on-chip shared memory, and registers. Centered around the codebook cache, we design an efficient computation engine that optimizes memory traffic during computations involving codebooks. This compute engine adopts the codebook-centric dataflow and fusion optimizations. Additionally, we provide adaptive heuristics to tailor parameter selection in our optimizations to diverse VQ configurations. Our optimizations achieve an average latency reduction of 46.13% compared to unoptimized versions. Compared to existing open-source implementations, our methods decrease latency by 64.36% to 99.1%. A final comparison with state-of-the-art element-wise quantization methods like AWQ and KVQuant shows that our VQ-LLM is practically viable, achieving latencies close or even better latencies to those at equivalent bit-widths, potentially offering greater accuracy.

cs.DC↗

arXiv2025

Deceptive Path Planning: A Bayesian Game Approach

This paper investigates how an autonomous agent can transmit information through its motion in an adversarial setting. We consider scenarios where an agent must reach its goal while deceiving an intelligent observer about its destination. We model this interaction as a dynamic Bayesian game between a mobile Attacker with a privately known goal and a Defender who infers the Attacker's intent to allocate defensive resources effectively. We use Perfect Bayesian Nash Equilibrium (PBNE) as our solution concept and propose a computationally efficient approach to find it. In the resulting equilibrium, the Defender employs a simple Markovian strategy, while the Attacker strategically balances deception and goal efficiency by stochastically mixing shortest and non-shortest paths to manipulate the Defender's beliefs. Numerical experiments demonstrate the advantages of our PBNE-based strategies over existing methods based on one-sided optimization.

eess.SY↗

arXiv2025

KPerfIR: Towards an Open and Compiler-centric Ecosystem for GPU Kernel Performance Tooling on Modern AI Workloads

In this work, we propose KPerfIR, a novel multilevel compiler-centric infrastructure to enable the development of customizable, extendable, and portable profiling tools tailored for modern artificial intelligence (AI) workloads on modern GPUs. Our approach integrates profiling capabilities directly into the compiler workflow, allowing profiling functionalities to be implemented as compiler passes, offering a programmable and reusable framework for performance analysis. This design bridges the gap between compilers and profilers, enabling fine-grained insights into complex optimization challenges such as overlapping the execution of fine-grained function units on GPUs. KPerfIR is integrated into the Triton infrastructure to highlight the power of a compiler-centric approach to advance performance analysis and optimization in the ever-evolving landscape of AI compilers. Our evaluation shows that our tool incurs low overhead (8.2%), provides accurate measurements (2% relative error), and delivers actionable insights into complicated GPU intra-kernel optimizations.

cs.DC↗

arXiv2025

An Efficient Private GPT Never Autoregressively Decodes

The wide deployment of the generative pre-trained transformer (GPT) has raised privacy concerns for both clients and servers. While cryptographic primitives can be employed for secure GPT inference to protect the privacy of both parties, they introduce considerable performance overhead.To accelerate secure inference, this study proposes a public decoding and secure verification approach that utilizes public GPT models, motivated by the observation that securely decoding one and multiple tokens takes a similar latency. The client uses the public model to generate a set of tokens, which are then securely verified by the private model for acceptance. The efficiency of our approach depends on the acceptance ratio of tokens proposed by the public model, which we improve from two aspects: (1) a private sampling protocol optimized for cryptographic primitives and (2) model alignment using knowledge distillation. Our approach improves the efficiency of secure decoding while maintaining the same level of privacy and generation quality as standard secure decoding. Experiments demonstrate a $2.1\times \sim 6.0\times$ speedup compared to standard decoding across three pairs of public-private models and different network conditions.

cs.CR↗

arXiv2025

WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training

In this work, we present WLB-LLM, a workLoad-balanced 4D parallelism for large language model training. We first thoroughly analyze the workload imbalance issue in LLM training and identify two primary sources of imbalance at the pipeline parallelism and context parallelism levels. Then, to address the imbalance issue, at the pipeline parallelism level, WLB-LLM incorporates a workload-aware variable-length document packing method to balance the computation and communication workload across micro-batches. Additionally, at the context parallelism level, WLB-LLM introduces a novel fine-grained per-document sharding strategy, ensuring each worker within a context parallelism group has an identical workload. Comprehensive experiments under different model scales demonstrate that WLB-LLM significantly mitigates the workload imbalance during 4D parallelism LLM training and achieves an average speedup of 1.23x when applying WLB-LLM in our internal LLM training framework.

cs.DC↗

arXiv2025

M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type

Large language models (LLMs) are one of the most important killer computer applications. The recent algorithmic advancement proposes a fine-grained group-wise quantization for LLMs, which treats a small set (e.g., 64) of values in a tensor as a compression unit. It effectively preserves the model accuracy without retraining, and has become the standard approach to efficiently deploy LLMs. On the other hand, there are works that propose various adaptive data types to better adapt to different distributions and further reduce the required bit length for LLMs. In this work, our detailed analysis unveils a key finding that while different tensors exhibit similar distributions, small groups can have markedly different distributions. As such, the group-level diversity requires a new level of adaptivity for which existing adaptive data types fail to provide. In this paper, we propose MANT, a mathematically adaptive numeric type, featuring a more flexible encoding paradigm with a wider range of data distribution and more efficient decodingcomputation fusion mechanism to address these challenges. Based on MANT, we develop a supporting framework to assign the appropriate data type for each group adaptively. Meanwhile, the dynamically generated Key-Value (KV) caches in LLMs introduce further complexity for real-time quantization. To tackle this, we propose an efficient real-time quantization mechanism. Besides, we implement a specific processing element (PE) to efficiently support MANT and incorporate a real-time quantization unit. By integrating these components into a systolic array, MANT unifies the group-wise weight and KV cache quantization and addresses the associated challenges. Our evaluation shows achieving, on average, 2.99x (up to 4.46x) speedup and 2.81x (up to 4.10x) energy reduction to the state-of-the-art LLM accelerator.

cs.AR↗

arXiv2024

Zero-Sum Games between Large-Population Teams: Reachability-based Analysis under Mean-Field Sharing

This work studies the behaviors of two large-population teams competing in a discrete environment. The team-level interactions are modeled as a zero-sum game while the agent dynamics within each team is formulated as a collaborative mean-field team problem. Drawing inspiration from the mean-field literature, we first approximate the large-population team game with its infinite-population limit. Subsequently, we construct a fictitious centralized system and transform the infinite-population game to an equivalent zero-sum game between two coordinators. We study the optimal coordination strategies for each team via a novel reachability analysis and later translate them back to decentralized strategies that the original agents deploy. We prove that the strategies are $ε$-optimal for the original finite-population team game, and we further show that the suboptimality diminishes when team size approaches infinity. The theoretical guarantees are verified by numerical examples.

eess.SY↗

arXiv2024

Accelerating Sparse DNNs Based on Tiled GEMM

Network pruning can reduce the computation cost of deep neural network (DNN) models. However, sparse models often produce randomly-distributed weights to maintain accuracy, leading to irregular computations. Consequently, unstructured sparse models cannot achieve meaningful speedup on commodity hardware built for dense matrix computations. Accelerators are usually modified or designed with structured sparsity-optimized architectures for exploiting sparsity. For example, the Ampere architecture introduces a sparse tensor core, which adopts the 2:4 sparsity pattern. We propose a pruning method that builds upon the insight that matrix multiplication generally breaks the large matrix into multiple smaller tiles for parallel execution. We present the tile-wise sparsity pattern, which maintains a structured sparsity pattern at the tile level for efficient execution but allows for irregular pruning at the global scale to maintain high accuracy. In addition, the tile-wise sparsity is implemented at the global memory level, and the 2:4 sparsity executes at the register level inside the sparse tensor core. We can combine these two patterns into a tile-vector-wise (TVW) sparsity pattern to explore more fine-grained sparsity and further accelerate the sparse DNN models. We evaluate the TVW on the GPU, achieving averages of $1.85\times$, $2.75\times$, and $22.18\times$ speedups over the dense model, block sparsity, and unstructured sparsity.

cs.DC↗

arXiv2023

The Eater and the Mover Game

This paper studies the idea of ``deception by motion'' through a two-player dynamic game played between a Mover who must retrieve resources at a goal location, and an Eater who can consume resources at two candidate goals. The Mover seeks to minimize the resource consumption at the true goal, and the Eater tries to maximize it. While the Mover has the knowledge about the true goal, the Eater cannot differentiate between the two candidates. Unlike existing works on deceptive motion control that measures the deceptiveness through the quality of inference made by a distant observer (an estimator), we incorporate their actions to directly measure the efficacy of deception through the outcome of the game. An equilibrium concept is then proposed without the notion of an estimator. We further identify a pair of equilibrium strategies and demonstrate that if the Eater optimizes for the worst-case scenario, hiding the intention (deception by ambiguity) is still effective, whereas trying to fake the true goal (deception by exaggeration) is not.

eess.SY↗

arXiv2023

Why Do Humans Twist Their Ankle: A Nonlinear Dynamical Stability Model for Lower Limb

Although ankle injuries resulting from postural instability are frequently observed during high-speed and intense physical activities, most current research has been limited to static or quasi-static models of the lower limb, or has focused solely on the ankle joint itself. In this study, to explain the kinetic mechanism underlying postural instability and ankle twists, we present a nonlinear dynamical model for the human lower limb that takes into account transient behavior and large rotations. The landing of the lower limb on the ground is modeled as a mechanical system with two degrees of freedom (DoFs). The configuration of the lower limb mechanism can be completely defined by the vertical displacement and the inclination angle. We quantify the postural stability of the lower limb using a dimensionless energy threshold. Numerical examples verify the effectiveness of this stability indicator and demonstrate that individuals with a normal foot have better postural stability compared to those with flat and high-arched feet, and are less likely to experience ankle injuries in jumping and landing scenarios.

physics.bio-ph↗