Searcharxiv⌕ Search

arXiv subjects

Haibo Chen

Publications and source records attributed to Haibo Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

CoAgent: Concurrency Control for Multi-Agent Systems

Multi-agent LLM systems -- coding agents, devops agents, document agents -- now routinely run several agents in parallel against the same git tree, Kubernetes cluster, or document. As soon as two of them mutate shared state, they enter the regime classical concurrency control has studied for decades, but classical mechanisms fit LLM agents poorly. A single agent transaction spans minutes of inference, read sets are broad and opaque rather than statically inferable, and the live state agents act on admits neither fork nor buffer, so writes take effect the moment they execute. Locks block long inference intervals; OCC abort-and-retry discards minutes of work on every conflict. This paper builds concurrency control on a capability classical transactions lack: the LLM inside each agent can judge whether a conflicting write invalidates its plan, and can repair exactly the operations that depended on it. Control therefore turns advisory: the runtime informs, the agent repairs. Our protocol, MTPO (Monotonic Trajectory Pre-Order), fixes a serialization order at launch, serves each read the order-filtered value, and applies writes speculatively in place; a one-way notification asks an affected reader to re-judge and patch its plan, while the framework mechanically undoes and reorders misplaced writes through the saga-style inverse each tool registers in advance. At quiescence the run is serializable in the pre-decided order. We realize MTPO as CoAgent, toolcall middleware whose privileged ToolSmith grows footprint-declared, undoable tools online. On ten contended workloads, CoAgent stays within 5\% of serial correctness at a $1.4\times$ speedup and near-serial token cost, where 2PL and OCC surrender nearly all concurrency gains; on a bash-only target system, it grows a 25-tool library online and lifts the task pass rate from 45/71 to 63/71 at $0.80\times$ the time and $0.86\times$ the cost.

cs.DC↗
arXiv2026

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback

LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per C/R, which severely bottlenecks deep search and large-scale fan-outs. This paper observes that subsequent checkpoints in AI agents are highly similar. Therefore, instead of full duplication, a sandbox should only duplicate the changes between consecutive checkpoints (Key Insight). However, it is non-trivial to realize the idea, mainly due to the missing OS supports. This paper proposes a new OS-level abstraction, DeltaState, to enable the change-based transactional C/R for AI agents with two co-designed OS mechanisms. First, DeltaFS enables change-based filesystem C/R by organizing the file states into layers and dynamically freezing the writable layer and inserting a new one during checkpoint, reducing file updates to copy-on-write, and making rollback a simple layer switch. Second, DeltaCR enables change-based process state C/R using incremental dumps, and accelerates rollback by bypassing traditional pipelines to directly fork() from a frozen template process. We then present DeltaBox, a novel agent sandbox achieving millisecond level C/R through the two new mechanisms. Evaluations on SWE-bench and RL micro-benchmarks show DeltaBox completes checkpoint and rollback in millisecond-level latency (14ms and 5ms, respectively), empowering agents to explore substantially more nodes under fixed time budgets.

cs.OS↗
arXiv2026

Representations of the N=1 Heisenberg-Virasoro superalgebra

We first define a class of non-weight modules over the N=1 Heisenberg-Virasoro superalgebra $\mathfrak{g}$, which are reducible modules. Then we give all submodules of such modules, and present the corresponding irreducible quotient modules which were exactly studied in \cite{DL}. Also, we prove that those modules constitute a complete classification of $U(\mathfrak{h})$-free modules of rank $2$ over $\mathfrak{g}$, where $\mathfrak{h}=\C L_{0}\oplus\C H_{0}$ is the degree-0 part of $\mathfrak{g}$. As an application, we obtain a class of weight $\mathfrak{g}$-modules from those non-weight $\mathfrak{g}$-modules by weighting functor. Furthermore, we study the non-weight modules over the four subalgebras of $\mathfrak{g}$: (i) the Heisenberg-Virasoro algebra; (ii) the Neveu-Schwarz algebra; (iii) the Fermion-Virasoro algebra; (iv) the Heisenberg-Clifford superalgebra. As far as we know, those non-weight Heisenberg-Virasoro modules were constructed in \cite{HCS}, but the structure of submodules was not clear. In this paper, we determine all submodules of them, and we show the corresponding irreducible quotient modules which were exactly defined in \cite{CG}.

math.RT↗
arXiv2026

ParaCell: Paravirtualized Secure Containers with Lightweight Intra-Container Isolation and Intent-Driven Memory Management

Secure containers isolate each container with its own kernel, mitigating shared-kernel attacks prevalent in traditional container systems. However, existing designs still face a fundamental isolation--performance trade-off. Nested-cloud deployments amplify the cost of VM exits and page-table management, while emerging agentic workloads expose bursty memory demand that requires fine-grained elasticity. We attribute this trade-off to two root causes. First, existing designs lack lightweight intra-container isolation primitives for frequent container user--kernel transitions. Second, the host treats container memory management as opaque, forcing reactive secondary faults and coarse-grained huge page mappings to amortize their cost. This paper presents ParaCell, a paravirtualized secure container runtime built on two insights. First, intra-address-space hardware protection primitives can provide lightweight intra-container isolation. ParaCell uses MPK-based XGates to isolate the container user and container kernel within a single address space, turning frequent user--kernel transitions into direct domain switches. Second, container kernel allocators already encode memory-management intent. ParaCell introduces Pager to interpose on allocation and free events, batch proactive GPA to HPA bindings and unbindings, and avoid reactive shadow page-table faults while preserving fine-grained memory elasticity. ParaCell is implemented as a drop-in replacement for RunV. Our experiments demonstrate that, across traditional cloud and emerging agent applications, ParaCell reduces latency by up to 57% and 79% over PVM, and by up to 33% and 88% over RunV, in bare-metal and nested setups, respectively. On agent workloads, ParaCell saves up to 35.6% memory compared with the state-of-the-art VM memory reclamation technique, HyperAlloc.

cs.OS↗
arXiv2026

Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting

Instilling creativity in text-to-image (T2I) generation presents a significant challenge, as it requires synthesized images to exhibit not only visual novelty and surprise, but also artistic value. Current T2I models, however, are largely optimized for literal text-image alignment with their data distribution, and their noise prediction networks constrain the generation to high-probability regions, consequently generating outputs that lack authentic creativity. To address this, we propose a Self-Creative Diffusion (SCDiff) model for meaningful T2I generations featuring two core modules: a learnable spatial weighting (LSW) module and a visual-semantic mixing loss (VSML). The LSW module designs a parametric Kaiser-Bessel window to reinforce central image features, fostering novel and surprising generation. The VSML module introduces a dual loss function: a similarity loss constrains that the new images align with its textual description, while a diversity loss maximizes its distinction from the original image, enhancing both semantic value and visual novelty. Extensive experiments demonstrate that our model substantially improves creativity, semantic alignment, and visual coherence, offering a simple yet powerful framework for generating creative objects.

cs.CV↗
arXiv2026

A Case for Agentic Tuning: From Documentation to Action in PostgreSQL

Documentation has long guided computer system tuning by distilling expert knowledge into per-parameter recommendations. Yet such guides capture only what experts conclude, discarding how they reason. This fundamental gap manifests in three concrete deficiencies: documentation grows stale as software evolves, fails under heterogeneous workloads, and ignores inter-parameter dependencies. We propose shifting from static documentation to dynamic action for system tuning. We introduce PerfEvolve, which translates expert tuning methodologies into executable skills that equip LLM-based agents to perform version-consistency verification, workload-specific profiling, and multi-parameter joint optimization. Evaluated on PostgreSQL under TPC-C and TPC-H benchmarks, PerfEvolve outperforms state-of-the-art documentation-driven tuning baselines by up to 35.2%. The tool is available at https://github.com/ISCAS-OSLab/PerfEvolve.

cs.SE↗
arXiv2026

A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning

Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large Language Models (LLMs) through alignment instruction tuning has become a mainstream paradigm for constructing Graph Language Models (GLMs), combining the generalization ability of LLMs with the structural modeling capacity of GNNs. However, existing GLMs that adopt GNNs as graph encoders largely overlook the problem of aligning GNN-encoded representations across domains and tasks with the LLM token space to obtain unified graph tokens, thereby limiting their ability to generalize across diverse graph data. To bridge this gap, we aim to incorporate a multi-domain, multi-task GNN encoder into GLMs and align its representations with LLMs to enable multi-domain, multi-task graph alignment instruction tuning. This alignment problem remains underexplored and poses two key challenges: 1) learning GNN-encoded representations that are simultaneously generalizable across domains and tasks and well aligned with textual semantics is difficult, due to substantial variations in graph structures, feature distributions, and supervision signals, together with the lack of textual-semantic alignment guidance in task-specific GNN training; 2) diverse graph data and task-specific instructions can exhibit different degrees of compatibility with the LLM token space during instruction tuning, leading to varying alignment difficulty and rendering a fixed alignment strategy suboptimal. To tackle these challenges, we propose UniGraphLM, a Unified Graph Language Model that incorporates a multi-domain, multi-task GNN encoder to learn generalizable graph representations aligned with textual semantics, and then adaptively aligns these representations with the LLM.

cs.LG↗
arXiv2026

Agentic AIs Are the Missing Paradigm for Out-of-Distribution Generalization in Foundation Models

Foundation models (FMs) are increasingly deployed in open-world settings where distribution shift is the rule rather than the exception. The out-of-distribution (OOD) phenomena they face -- knowledge boundaries, capability ceilings, compositional shifts, and open-ended task variation -- differ in kind from the settings that have shaped prior OOD research, and are further complicated because the pretraining and post-training distributions of modern FMs are often only partially observed. Our position is that OOD for foundation models is a structurally distinct problem that cannot be solved within the prevailing model-centric paradigm, and that agentic systems constitute the missing paradigm required to address it. We defend this claim through four steps. First, we give a stage-aware formalization of OOD that accommodates partially observed multi-stage training distributions. Second, we prove a parameter coverage ceiling: there exist practically relevant inputs that no model-centric method (training-time or test-time) can handle within tolerance $\varepsilon$, for reasons intrinsic to parameter-based representation. Third, we characterize agentic OOD systems by four structural properties -- perception, strategy selection, external action, and closed-loop verification -- and show that they strictly extend the reachable set beyond the ceiling. Fourth, we respond to seven counterarguments, conceding two, and outline a research agenda. We do not claim that agentic methods subsume model-centric ones; we argue that the two are complementary, and that progress on FM-OOD requires explicit recognition of the agentic paradigm as a first-class research direction.

cs.LG↗
arXiv2026

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses

LLM agents increasingly adopt skills as a reusable unit of composition. While skills are shared across diverse agent platforms, current systems treat them as raw context, causing the same skill to behave inconsistently for different agents. This fragility undermines skill portability and execution efficiency. To address this challenge, we analyze 118,000 skills and draw inspiration from traditional compiler design. We treat skills as code and LLMs as heterogeneous processors. To make portability actionable, we decompose a skill's requirements into a set of primitive capabilities, and measure how well each model-harness pair supports them. Based on these capability profiles, we propose SkVM, a compilation and runtime system designed for portable and efficient skill execution. At compile time, SkVM performs capability-based compilation, environment binding, and concurrency extraction. At runtime, SkVM applies JIT code solidification and adaptive recompilation for performance optimization. We evaluate SkVM across eight LLMs of varying scales and three agent harnesses, covering SkillsBench and representative skill tasks. Results demonstrate that SkVM significantly improves task completion rates across different models and environments while reducing token consumption by up to 40%. In terms of performance, SkVM achieves up to 3.2x speedup with enhanced parallelism, and 19-50x latency reduction through code solidification.

cs.SE↗
arXiv2026

From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents

Computer-use agents (CUAs) powered by large language models (LLMs) have emerged as a promising approach to automating computer tasks, yet they struggle with the existing human-oriented OS interfaces - graphical user interfaces (GUIs). GUIs force LLMs to decompose high-level goals into lengthy, error-prone sequences of fine-grained actions, resulting in low success rates and an excessive number of LLM calls. We propose Declarative Model Interface (DMI), an abstraction that transforms existing GUIs into three declarative primitives: access, state, and observation, thereby providing novel OS interfaces tailored for LLM agents. Our key idea is policy-mechanism separation: LLMs focus on high-level semantic planning (policy) while DMI handles low-level navigation and interaction (mechanism). DMI does not require modifying the application source code or relying on application programming interfaces (APIs). We evaluate DMI with Microsoft Office Suite (Word, PowerPoint, Excel) on Windows. Integrating DMI into a leading GUI-based agent baseline improves task success rates by 67% and reduces interaction steps by 43.5%. Notably, DMI completes over 61% of successful tasks with a single LLM call.

cs.OS↗
arXiv2026

On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding

Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end budgets on edge hardware. Revisiting the objective of top-K selection, we reveal that only relative rankings matter, not exact per-candidate scores. We further observe sequence-level sparsity: relative rankings progressively stabilize in intermediate layers, enabling early pruning prior to completing full inference. Building on this insight, we propose monolithic forwarding and develop a training-free inference system, PRISM. By maintaining a global view of all candidates, it reduces latency through progressive cluster pruning. It also bounds peak memory usage by strategically overlapping I/O with computation via overlapped layer streaming and chunked execution. We evaluate PRISM against state-of-the-art baselines on rerankers from 0.6 B to 8 B parameters across Apple M2 and RTX 5070. PRISM consistently reduces latency by up to 89.2% and peak memory by up to 91.3% in microbenchmarks, without compromising precision. Across three real-world on-device AI applications, PRISM lowers latency by 11.6%-51.0% and peak memory by 18.6%-77.8%, demonstrating substantial improvements in efficiency and deployability.

cs.LG↗
arXiv2026

DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline

Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible combinations of input data, their training efficiency suffers from two major issues: pipeline stage imbalance caused by heterogeneous model architectures, and training data dynamicity stemming from the diversity of multimodal data. In this paper, we present DIP, a dynamic and modality-aware pipeline scheduling framework designed for LMM training. DIP tackles the challenge of dynamic imbalance via two key techniques: (1) separating computations of different modalities into dedicated pipeline segments to balance workloads within a continuous set of stages; (2) dynamically splitting input data into finer-grained, modality-specific sub-microbatches to balance workloads across these segments. By asynchronously generating pipeline schedules on idle CPU resources during training, DIP dynamically tailors stage executions to each input batch without stalling the training process. We validate DIP on a diverse set of five LMMs, ranging from 12B to 94B parameters and including vision-language and diffusion models. Experimental results show that our system achieves up to 97.3% higher throughput compared to state-of-the-art systems, demonstrating strong adaptability to fluctuating multimodal training workloads.

cs.DC↗
arXiv2026

KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially improves serving throughput and latency. However, there is limited understanding of how LLM serving benefits from KV\$ caching, where system design decisions like cache eviction policies are highly workload-dependent. In this paper, we present the first systematic characterization of the KV\$ workload patterns from one of the leading LLM service providers. We draw observations that were not covered by previous studies focusing on synthetic workloads, including: KV\$ reuses are skewed across requests, where reuses between single-turn requests are equally important as multi-turn requests; the reuse time and probability are diverse considering all requests, but for a specific request category, the pattern tends to be predictable; and the overall cache size required for an ideal cache hit ratio is moderate. Based on the characterization, we further propose a workload-aware cache eviction policy that improves the serving performance under real-world traces, especially with limited cache capacity.

cs.DC↗
arXiv2026

Sharpen the Spec, Cut the Code: A Case for Generative File System with SYSSPEC

File systems are critical OS components that require constant evolution to support new hardware and emerging application needs. However, the traditional paradigm of developing features, fixing bugs, and maintaining the system incurs significant overhead, especially as systems grow in complexity. This paper proposes a new paradigm, generative file systems, which leverages Large Language Models (LLMs) to generate and evolve a file system from prompts, effectively addressing the need for robust evolution. Despite the widespread success of LLMs in code generation, attempts to create a functional file system have thus far been unsuccessful, mainly due to the ambiguity of natural language prompts. This paper introduces SYSSPEC, a framework for developing generative file systems. Its key insight is to replace ambiguous natural language with principles adapted from formal methods. Instead of imprecise prompts, SYSSPEC employs a multi-part specification that accurately describes a file system's functionality, modularity, and concurrency. The specification acts as an unambiguous blueprint, guiding LLMs to generate expected code flexibly. To manage evolution, we develop a DAG-structured patch that operates on the specification itself, enabling new features to be added without violating existing invariants. Moreover, the SYSSPEC toolchain features a set of LLM-based agents with mechanisms to mitigate hallucination during construction and evolution. We demonstrate our approach by generating SPECFS, a concurrent file system. SPECFS demonstrates equivalent level of correctness to that of a manually-coded baseline across hundreds of regression tests. We further confirm its evolvability by seamlessly integrating 10 real-world features from Ext4. Our work shows that a specification-guided approach makes generating and evolving complex systems not only feasible but also highly effective.

cs.OS↗
arXiv2026

ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler

As large language models (LLMs) move from research to production, understanding how inference engines behave in real time has become both essential and elusive. Unlike general-purpose engines such as ONNX Runtime, today's LLM inference systems offer little operator-level visibility, leaving developers blind to where time and resources go. Even basic questions -- is this workload memory-bound or compute-bound? -- often remain unanswered. To close this gap, we develop a fine-grained, non-intrusive profiling framework for modern LLM inference engines, exemplified by llama-cpp but applicable to similar runtime architectures. Built on extended Berkeley Packet Filter (eBPF) technology, our system dynamically attaches probes to runtime functions across multiple layers -- without modifying or recompiling the source. It transforms collected traces into rich visualizations of operators, graphs, timelines, and hardware counter trends, exposing how dense inference, Mixture-of-Experts routing, and operator offloading behave in practice. With less than 4% runtime overhead and high profiling fidelity, our framework makes LLM inference both transparent and diagnosable, turning performance profiling into a practical tool for optimization, scheduling, and resource-aware deployment.

cs.SE↗
arXiv2026

Out-of-Distribution Generalization in Graph Foundation Models

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when applied beyond their training distributions. In practice, distribution shifts may arise from changes in graph structure, domain semantics, available modalities, or task formulations. To address these challenges, graph foundation models (GFMs) have recently emerged, aiming to learn general-purpose representations through large-scale pretraining across diverse graphs and tasks. In this survey, we review recent progress on GFMs from the perspective of out-of-distribution (OOD) generalization. We first discuss the main challenges posed by distribution shifts in graph learning and outline a unified problem setting. We then organize existing approaches based on whether they are designed to operate under a fixed task specification or to support generalization across heterogeneous task formulations, and summarize the corresponding OOD handling strategies and pretraining objectives. Finally, we review common evaluation protocols and discuss open directions for future research. To the best of our knowledge, this paper is the first survey for OOD generalization in GFMs.

cs.LG↗
arXiv2026

"Range as a Key" is the Key! Fast and Compact Cloud Block Store Index with RASK

In cloud block store, indexing is on the critical path of I/O operations and typically resides in memory. With the scaling of users and the emergence of denser storage media, the index has become a primary memory consumer, causing memory strain. Our extensive analysis of production traces reveals that write requests exhibit a strong tendency to target continuous block ranges in cloud storage systems. Thus, compared to current per-block indexing, our insight is that we should directly index block ranges (i.e., range-as-a-key) to save memory. In this paper, we propose RASK, a memory-efficient and high-performance tree-structured index that natively indexes ranges. While range-as-a-key offers the potential to save memory and improve performance, realizing this idea is challenging due to the range overlap and range fragmentation issues. To handle range overlap efficiently, RASK introduces the log-structured leaf, combined with range-tailored search and garbage collection. To reduce range fragmentation, RASK employs range-aware split and merge mechanisms. Our evaluations on four production traces show that RASK reduces memory footprint by up to 98.9% and increases throughput by up to 31.0x compared to ten state-of-the-art indexes.

cs.OS↗
arXiv2026

FalconFS: Distributed File System for Large-Scale Deep Learning Pipeline

Client-side metadata caching has long been considered an effective method for accelerating metadata operations in distributed file systems (DFSs). However, we have found that client-side state (e.g., caching) is not only ineffective but also consumes valuable memory resources in the deep learning pipelines. We thus propose FalconFS, a DFS optimized for deep learning pipelines with the stateless-client architecture. Specifically, instead of performing client-side path resolution and caching, FalconFS efficiently resolves paths on the server side using hybrid metadata indexing and lazy namespace replication. FalconFS also boosts server concurrency with concurrent request merging and provides easy deployment with VFS shortcut. Evaluations against CephFS and Lustre show that FalconFS achieves up to 5.72$\times$ throughput for small file read/write and up to 12.81$\times$ throughput for deep learning model training. FalconFS has been running in Huawei autonomous driving system's production environment with 10,000 NPUs for one year and has been open-sourced.

cs.DC↗