arXiv subjects

Fengming Zhu

Publications and source records attributed to Fengming Zhu.

13 recordsLinked to original sources

arXiv2026

CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits

AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost exclusively on CUDA and Triton, leaving hardware ecosystems with less-exposed programming models without a common evaluation baseline. We present CANN Bench, an open benchmark for AI-generated operator code on Huawei's Ascend NPU. The current release covers 53 operators and 1060 test cases organized into four difficulty tiers -- from simple elementwise primitives to MoE dispatch and FlashAttention kernels -- spanning FP16, BF16, FP32, and INT8 precision formats. Evaluation adopts a \textbf{three-dimensional weighted composite score} that treats compilation, functional correctness, and performance as independent axes, providing a principled reward signal for kernel-generation agents. Performance is graded against an out-of-the-box PyTorch-on-Ascend baseline and an analytical per-case Hardware-Anchored Performance (HAP) limit on real NPU hardware, ensuring scores reflect genuine optimization headroom rather than measurement artifacts. The evaluation harness is designed to resist reward hacking from the ground up. CANN Bench is versioned within the official CANN repository and is designed for long-term community co-construction, providing the Ascend ecosystem with a quantitative, reproducible, and sustainably maintained yardstick for AI operator-authoring capability.

cs.AI↗

arXiv2026

ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response

While passive agents merely follow instructions, proactive agents align with higher-level objectives, such as assistance and safety by continuously monitoring the environment to determine when and how to act. However, developing proactive agents is hindered by the lack of specialized resources. To address this, we introduce ProAct-75, a benchmark designed to train and evaluate proactive agents across diverse domains, including assistance, maintenance, and safety monitoring. Spanning 75 tasks, our dataset features 91,581 step-level annotations enriched with explicit task graphs. These graphs encode step dependencies and parallel execution possibilities, providing the structural grounding necessary for complex decision-making. Building on this benchmark, we propose ProAct-Helper, a reference baseline powered by a Multimodal Large Language Model (MLLM) that grounds decision-making in state detection, and leveraging task graphs to enable entropy-driven heuristic search for action selection, allowing agents to execute parallel threads independently rather than mirroring the human's next step. Extensive experiments demonstrate that ProAct-Helper outperforms strong closed-source models, improving trigger detection mF1 by 6.21%, saving 0.25 more steps in online one-step decision, and increasing the rate of parallel actions by 15.58%.

cs.RO↗

arXiv2025

A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind

Originating in psychology, $\textit{Theory of Mind}$ (ToM) has attracted significant attention across multiple research communities, especially logic, economics, and robotics. Most psychological work does not aim at formalizing those central concepts, namely $\textit{goals}$, $\textit{intentions}$, and $\textit{beliefs}$, to automate a ToM-based computational process, which, by contrast, has been extensively studied by logicians. In this paper, we offer a different perspective by proposing a computational framework viewed through the lens of game theory. On the one hand, the framework prescribes how to make boudedly rational decisions while maintaining a theory of mind about others (and recursively, each of the others holding a theory of mind about the rest); on the other hand, it employs statistical techniques and approximate solutions to retain computability of the inherent computational problem.

cs.AI↗

arXiv2025

Diminution: On Reducing the Size of Grounding ASP Programs

Answer Set Programming (ASP) is often hindered by the grounding bottleneck: large Herbrand universes generate ground programs so large that solving becomes difficult. Many methods employ ad-hoc heuristics to improve grounding performance, motivating the need for a more formal and generalizable strategy. We introduce the notion of diminution, defined as a selected subset of the Herbrand universe used to generate a reduced ground program before solving. We give a formal definition of diminution, analyze its key properties, and study the complexity of identifying it. We use a specific encoding that enables off-the-shelf ASP solver to evaluate candidate subsets. Our approach integrates seamlessly with existing grounders via domain predicates. In extensive experiments on five benchmarks, applying diminutions selected by our strategy yields significant performance improvements, reducing grounding time by up to 70% on average and decreasing the size of grounding files by up to 85%. These results demonstrate that leveraging diminutions constitutes a robust and general-purpose approach for alleviating the grounding bottleneck in ASP.

cs.AI↗

arXiv2025

Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria

Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games. We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies. Those theoretic insights are later verified on several sequential decision-making testbeds, including the $\textit{Iterated Prisoner's Dilemma}$, the $\textit{Iterated Traveler's Dilemma}$, and the $\textit{Pursuit}$ domain. This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts. The code is available at $\texttt{https://github.com/Fernadoo/Const-Mem.}$

cs.GT↗

arXiv2025

Single-Agent Planning in a Multi-Agent System: A Unified Framework for Type-Based Planners

We consider a general problem where an agent is in a multi-agent environment and must plan for herself without any prior information about her opponents. At each moment, this pivotal agent is faced with a trade-off between exploiting her currently accumulated information about the other agents and exploring further to improve future (re-)planning. We propose a theoretic framework that unifies a spectrum of planners for the pivotal agent to address this trade-off. The planner at one end of this spectrum aims to find exact solutions, while those towards the other end yield approximate solutions as the problem scales up. Beyond theoretical analysis, we also implement \textbf{13} planners and conduct experiments in a specific domain called \textit{multi-agent route planning} with the number of agents \textbf{up to~50}, to compare their performaces in various scenarios. One interesting observation comes from a class of planners that we call \textit{safe-agents} and their enhanced variants by incorporating domain-specific knowledge, which is a simple special case under the proposed general framework, but performs sufficiently well in most cases. Our unified framework, as well as those induced planners, provides new insights on multi-agent decision-making, with potential applications to related areas such as mechanism design.

cs.MA↗

arXiv2025

The Combined Problem of Online Task Assignment and Lifelong Path Finding in Logistics Warehouses: Rule-Based Systems Matter

We study the combined problem of online task assignment and lifelong path finding, which is crucial for the logistics industries. However, most literature either (1) focuses on lifelong path finding assuming a given task assigner, or (2) studies the offline version of this problem where tasks are known in advance. We argue that, to maximize the system throughput, the online version that integrates these two components should be tackled directly. To this end, we introduce a formal framework of the combined problem and its solution concept. Then, we design a rule-based lifelong planner under a practical robot model that works well even in environments with severe local congestion. Upon that, we automate the search for the task assigner with respect to the underlying path planner. Simulation experiments conducted in warehouse scenarios at Meituan, one of the largest shopping platforms in China, demonstrate that (a)in terms of time efficiency, our system requires only 83.77% of the execution time needed for the currently deployed system at Meituan, outperforming other SOTA algorithms by 8.09%; (b)in terms of economic efficiency, ours can achieve the same throughput with only 60% of the agents currently in use. The code and demos are available at https://github.com/Fernadoo/Online-TAPF.

cs.MA↗

arXiv2025

To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization

Recent advances in mathematical problem-solving with language models (LMs) integrate chain-of-thought (CoT) reasoning and code execution to harness their complementary strengths. However, existing hybrid frameworks exhibit a critical limitation: they depend on externally dictated instructions or rigid code-integration templates, lacking metacognitive awareness -- the capacity to dynamically evaluate intrinsic capabilities and autonomously determine when and how to integrate tools. This rigidity motivates our study of autonomous code integration, enabling models to adapt tool-usage strategies as their reasoning abilities evolve during training. While reinforcement learning (RL) shows promise for boosting LLM reasoning at scale (e.g., DeepSeek-R1), we demonstrate its inefficiency in learning autonomous code integration due to inadequate exploration of the vast combinatorial space of CoT-code interleaving patterns. To address this challenge, we propose a novel Expectation-Maximization (EM) framework that synergizes structured exploration (E-step) with off-policy RL optimization (M-step), creating a self-reinforcing cycle between metacognitive tool-use decisions and evolving capabilities. Experiments reveal our method achieves superior results through improved exploration. Notably, our 7B model improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT.

cs.AI↗

arXiv2024

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination

Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning (MARL) methods usually do not explicitly take consensus into consideration, which may cause miscoordination problem. In this paper, we propose a model-based consensus mechanism to explicitly coordinate multiple agents. The proposed Multi-agent Goal Imagination (MAGI) framework guides agents to reach consensus with an Imagined common goal. The common goal is an achievable state with high value, which is obtained by sampling from the distribution of future states. We directly model this distribution with a self-supervised generative model, thus alleviating the "curse of dimensinality" problem induced by multi-agent multi-step policy rollout commonly used in model-based methods. We show that such efficient consensus mechanism can guide all agents cooperatively reaching valuable future states. Results on Multi-agent Particle-Environments and Google Research Football environment demonstrate the superiority of MAGI in both sample efficiency and performance.

cs.AI↗

arXiv2023

Agent-Based Modelling for Real-World Stock Markets under Behavioral Economic Principles

The reproduction of realistic dynamics in financial markets is of great significance, as it enhances our understanding of market evolution beyond other physical processes, and facilitates the development and backtesting of investment strategies. Most existing literature approaches this issue as a time series forecasting problem, which often faces challenges such as 1) overfitting historical data, 2) failing to reconstruct stylized facts, and 3) limiting users' ability to conduct counterfactual analyses. To address these limitations, we employ agent-based modeling (ABM) for market simulation, where each trader acts as an autonomous agent guided by established behavioral-economic principles. The parameters of the agent model are subsequently calibrated using deep learning techniques. Additionally, we align our agent model with publicly available economic indices, such as the Consumer Price Index (CPI), to enhance the explainability of our system's outcomes. Our experiments demonstrate that the ABM method effectively reproduces market dynamics with a confidence level of 90%, accurately reflecting well-known stylized facts. Furthermore, the calibration process proves to be more computationally efficient compared to other existing methods that perform simulation-based inference. We also present case studies illustrating the correlation between agent parameters and economic indices.

cs.MA↗

arXiv2023

Computing Universal Plans for Partially Observable Multi-Agent Routing Using Answer Set Programming

Multi-agent routing problems have gained significant attention recently due to their wide range of industrial applications, ranging from logistics warehouse automation to indoor service robots. Conventionally, they are modeled as classical planning problems. In this paper, we argue that it can be beneficial to formulate them as universal planning problems, particularly when the agents are autonomous entities and may encounter unforeseen situations. We therefore propose universal plans, also known as policies, as the solution concept, and implement a system based on Answer Set Programming (ASP) to compute them. Given an arbitrary two-dimensional map and a profile of goals for a group of partially observable agents, the system translates the problem configuration into logic programs and finds a feasible universal plan for each agent, mapping its observations to actions while ensuring that there are no collisions with other agents. We use the system to conduct experiments and obtain findings regarding the types of goal profiles and environments that lead to feasible policies, as well as how feasibility may depend on the agents' sensors. We also demonstrate how users can customize action preferences to compute more efficient policies, even (near-)optimal ones. The code is available at https://github.com/Fernadoo/MAPF_ASP.

cs.MA↗

arXiv2021

TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations

Deep reinforcement learning (DRL) has achieved super-human performance on complex video games (e.g., StarCraft II and Dota II). However, current DRL systems still suffer from challenges of multi-agent coordination, sparse rewards, stochastic environments, etc. In seeking to address these challenges, we employ a football video game, e.g., Google Research Football (GRF), as our testbed and develop an end-to-end learning-based AI system (denoted as TiKick) to complete this challenging task. In this work, we first generated a large replay dataset from the self-playing of single-agent experts, which are obtained from league training. We then developed a distributed learning system and new offline algorithms to learn a powerful multi-agent AI from the fixed single-agent dataset. To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios. Extensive experiments further show that our pre-trained model can accelerate the training process of the modern multi-agent algorithm and our method achieves state-of-the-art performances on various academic scenarios.

cs.AI↗

arXiv2018

Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry

Combining cameras and inertial measurement units (IMUs) has been proven effective in motion tracking, as these two sensing modalities offer complementary characteristics that are suitable for fusion. While most works focus on global-shutter cameras and synchronized sensor measurements, consumer-grade devices are mostly equipped with rolling-shutter cameras and suffer from imperfect sensor synchronization. In this work, we propose a nonlinear optimization-based monocular visual inertial odometry (VIO) with varying camera-IMU time offset modeled as an unknown variable. Our approach is able to handle the rolling-shutter effects and imperfect sensor synchronization in a unified way. Additionally, we introduce an efficient algorithm based on dynamic programming and red-black tree to speed up IMU integration over variable-length time intervals during the optimization. An uncertainty-aware initialization is also presented to launch the VIO robustly. Comparisons with state-of-the-art methods on the Euroc dataset and mobile phone data are shown to validate the effectiveness of our approach.

cs.CV↗