arXiv subjects

Ying Liu

Publications and source records attributed to Ying Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes

Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes constitute unearned passes; their proportion among all passes defines the integrity gap. As agents improve, benchmark surfaces that once seemed harmless can become exploitable, making benchmark validity an ongoing maintenance problem. We introduce a process-verification framework that audits passing trajectories, distinguishes evidenced reward hacking from verifier weakness, and localizes exploitable surfaces for repair. Across 3,810 passing trajectories from 29 model-benchmark cohorts, confirmed violations often increase with model generation but not monotonically. On SWEBench Pro V1.0, confirmed violation rates rise from 24% to 73% between Opus 4.7 and Fable 5 on matched tasks; later cohorts fall to 11% for Fable 5.1 and 0% for GPT-6 Astra. These comparisons are descriptive: configurations were not normalized, and the latest models also pass fewer exploitable tasks. Violations concentrate around a small set of recurring surfaces, especially unintended access to reference solutions through git history. Three repair case studies across two benchmarks show why blocking a recorded exploit is insufficient: the same protected information can remain accessible through another route. Therefore, we combine minimal patches with exploit replay and fresh agent evaluation, auditing new passes under the original standard. No evaluated attempt against the final patches reached the protected channel, and every post-patch pass was judged legitimate. Benchmark integrity requires ongoing maintenance: audit passing behavior, repair the enabling surface, and re-evaluate both exploit access and legitimate solvability.

cs.AI↗

arXiv2026

CascadeEP: Asynchronous Expert Execution for MoE Prefill under Attention Imbalance

Mixture-of-experts (MoE) serving commonly deploys data and expert parallelism (DEP): attention replicas run distinct request batches while routed experts are sharded across an expert-parallel (EP) group. During prefill, attention replicas finish dispatch at different times, but synchronous EP delays expert feed-forward network (FFN) computation until routed inputs from all replicas are ready. Request schedulers seek to balance load while reusing the key-value (KV) cache of shared prompt prefixes to avoid redundant prefill computation. These goals can conflict when a replica holding a matching prefix is already overloaded, leaving residual attention imbalance. We present ASYNCEP, a distributed execution engine for MoE prefill. ASYNCEP proposes three mechanisms. Asynchronous EP allows expert computation to start before tokens from all attention replicas are ready. streamFFN batches ready tokens to balance early execution with FFN computation efficiency. Opportunistic expert weight fetching (OEWF) allows a faster replica to fetch expert weights and execute unstarted work from other GPUs. We evaluate ASYNCEP on DeepSeek-V4-Flash, DeepSeek-V4-Pro, and GLM-5.3, and our results show that ASYNCEP achieves up to 1.48x speedup in p95 time-to-first-token (TTFT) and improves the inference throughput by up to 1.17x.

cs.DC↗

arXiv2026

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.

cs.LG↗

arXiv2026

Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead

Small differences on coding-agent leaderboards are often read as an ordering of systems. We audit whether the published verdicts support this reading, using 254 SWE-bench submissions across four splits without running models. On Verified, the leading two entries each resolve 396 of 500 instances. The top ten share 285 successes and 51 failures, leaving 164 instances that distinguish their outcomes. Frontier solution sets have median nesting 0.935 against a score-implied baseline of 0.774, indicating strongly shared successes. Scores also depend on the evaluated model-scaffold pair: observed within-model scaffold ranges reach 29.8 percentage points, compared with the 8.8-point spread of the top thirty. Six of nine cell-mean interaction tests remain significant after Holm correction, although this observational design does not identify causal scaffold effects. Exact paired McNemar tests separate none of the 29 adjacent Verified top-thirty pairs at alpha=0.05, while the larger Test split separates 14 of 23. A stated leader-based rule yields three descriptive tiers, or two after Holm correction; non-rejection does not establish equivalence. We release the partition and a five-step audit protocol that profiles shared outcomes, tests paired differences, reports grouping sensitivity, and estimates the instance budget needed for resolution. The results motivate reporting comparison-set-specific resolution and model-scaffold provenance instead of interpreting small aggregate gaps as established rank differences.

cs.SE↗

arXiv2026

C$^2$Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation

Zero-shot vision-and-language navigation in continuous environments (VLN-CE) increasingly places foundation vision-language models (VLMs) inside the navigation loop. Existing systems commonly request cardinal outputs such as waypoints, pixels, headings, progress values, or absolute arrival decisions, coupling a generative response to geometric magnitude or an irreversible commitment. We study a complementary model-robot interface: the VLM compares controller-constructed alternatives, while geometry, thresholds, action magnitude, and execution remain on the physical side. We instantiate this idea in C2Nav, a training-free framework with three coordinated faculties. Seeing performs ordinal Gaze Election over physically vetted candidate views; Remembering maintains a compact route sketch and compares adjacent instruction-leg hypotheses; and Arriving combines a hesitation ladder, look-back comparison, and revocable walk-back for reliable stopping. On the public OpenNav R2R-CE 100 protocol, C2Nav with Qwen3-VL-8B-Instruct obtains 41.0% OSR, 31.0% SR, and 16.7% SPL, while the same interface with the standard GPT-5.5 model reaches 54.0% OSR, 44.0% SR, and 29.0% SPL. Whole-faculty ablations reduce SR to 14.0% without Seeing, 25.0% without Remembering, and 29.0% without Arriving. Matched role inversions that replace only the comparative answer form with cardinal/absolute questions reduce SR to 12.0%, 28.0%, and 21.0% in the spatial, transition, and terminal slots, respectively. The results indicate that a constrained decision interface and stronger VLM reasoning are complementary rather than interchangeable.

cs.RO↗

arXiv2026

Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration

Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typically rely either on trained routers, which tie routing decisions to a fixed task and model pool, or on raw-confidence cascades, whose thresholds lack consistent reliability semantics across heterogeneous models. Consequently, these approaches adapt poorly to changing model pools and deployment budgets. We propose Calibration-Aware Uncertainty Cascades (CAUC), a simple post-hoc framework that independently calibrates each model's confidence and selects deployment policies using validation data. The resulting calibrated confidence scores establish a common reliability scale for accepting an early prediction, invoking a stronger model, or selectively combining model outputs. This unified decision criterion decouples deployment policies from any particular model pool or operating budget. We further show theoretically that calibration gives confidence thresholds an explicit selective-risk interpretation, whereas uncalibrated scores offer no comparable reliability guarantee. Extensive experiments demonstrate that, across six language benchmarks, CAUC achieves an average relative accuracy improvement of 1.9% over strong-model-only inference while avoiding approximately 47% of strong-model calls. On image classification benchmarks, it maintains or improves predictive performance while reducing measured GFLOPs by up to 57%.

cs.AI↗

arXiv2026

Qwen-Audio-3.0-ASR Technical Report

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.

cs.CL↗

arXiv2026

READY or Not: Reliable Enterprise Agent Deployment

An AI agent can perform well on benchmarks and still be unsuitable for deployment. Existing AI-agent benchmarks measure whether an agent can complete realistic professional work, whereas enterprise deployment asks a different question: whether an agent can meet a required reliability level, under acceptable human oversight, and at tolerable cost. We introduce Reliable Enterprise Agent Deployment (READY), a framework for qualifying AI agents for deployment on enterprise workflows. READY preserves each workflow's own definition of successful execution while applying a common qualification procedure. Given an agent, a workflow, and a class of candidate oversight policies, READY measures the reliability and operating cost of the human-AI system, selects the minimum-cost policy that satisfies a specified reliability target, and statistically qualifies it on held-out cases. The resulting deployment profile characterizes the supported operating point: reliability, human-oversight burden, and cost. READY is implemented as an open testbed that decouples workflow specification, execution, evaluation, and qualification, and runs on existing agent-evaluation infrastructure. In an end-to-end clinical-audit case study spanning 16 agent systems and 750 cases, READY reveals differences hidden by autonomous performance: two systems separated by only 0.3 points in autonomous accuracy (72.8% vs. 72.5%) require 39.2% versus 29.6% human review, respectively, to qualify at the same 76% reliability target under the evaluated oversight policy. READY thus shifts enterprise agent evaluation from how well can the agent perform the work? to under what conditions, and at what cost, can it be reliably deployed? By making those conditions explicit and statistically testable, READY provides a basis for comparing agent systems, setting oversight requirements, and making evidence-based deployment decisions.

cs.AI↗

arXiv2026

Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models

Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image is compressed into a low-resolution global view. Allocating more visual tokens to every query improves some OCR and document cases, but it spends computation indiscriminately and can disturb tasks that rely on global context. We propose GapSight, a framework for learning visual re-reading: a VLM first takes a global glance, then selectively returns to a free-form region when the question calls for local evidence. The supervision comes from the target model's own failure signal. Offline, we compare answer loss or multiple-choice option margin under a global-only view and candidate crop-augmented views; crops that improve the target answer become model-specific review labels. A lightweight free-form crop router distills these labels into a one-shot inference policy that predicts whether to review, expected utility, and a continuous crop box from the global state. Across LLaVA-1.5-7B, InternVL2.5-8B, and Qwen2-VL-2B-Instruct, GapSight improves the Base no-zoom baseline on six benchmarks spanning OCR, documents, charts, infographics, VStarBench, and MME-RealWorld-Lite. On InternVL2.5-8B, GapSight raises the six-benchmark average from 52.25 to 64.29, above CropVLM (57.16), ViCrop (55.84), and ZoomRefine (54.43). Mechanism analyses show that the router rescues concrete wrong answers, adapts its action rate by task, and forms a favorable token-performance profile. These results position loss-gap supervision as a practical route to teaching VLMs when and where to look again.

cs.CV↗

arXiv2026

TTPO: Test-Time Policy Optimization

Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token. We observe that this failure mode is asymmetric: rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct. Building on this observation, we propose Test-Time Policy Optimization (TTPO), an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL. Token-level selection further refines both branches: distillation down-weights already-converged positions, while RL penalizes only confident errors. Both updates remain well-grounded even under frequent pseudo-label errors, and majority-vote routing yields tighter self-supervision as the model improves. Without any labels, TTPO matches label-supervised OPSD on five competition-level benchmarks, raises Qwen3-1.7B from 38.0% to 45.2% in TTT, yields +25.2% to +36.4% without thinking, and shows strong cross-task generalization.

cs.CL↗

arXiv2026

Min-Max Regret Task Allocation and Planning of Heterogeneous Multi-Robot System in Partially Known Environments

Efficient task allocation for large-scale Heterogeneous Multi-Robot Systems (HMRS) is critical, yet dealing with complex temporal logic tasks in partially known environment (PKE) remains a computational bottleneck. Existing approaches often struggle to balance exploring uncertain regions and exploiting known resources, while also suffering from exponential computational complexity. To address these issues, this paper presents a robust planning framework that simultaneously handles high-level logical constraints and environmental uncertainty without sacrificing scalability. We formulate the problem as a min-max regret optimization, proposing a Region-Binding Atomic Proposition (RbAP) to capture resource uncertainty within the automaton structure. To solve this, we propose the Extended Planning Decision Tree (E-PDT) equipped with a novel Regret-based Branch-and-Bound (BnB) strategy. Unlike traditional methods that rely on prior probabilities or worst-case analysis, our approach dynamically prunes suboptimal policies, effectively balancing the need for information gathering (exploration) and task completion (exploitation). Theoretical analysis confirms the feasibility and completeness of our approach. Extensive numerical and physical experiments demonstrate that the proposed framework achieves near-linear scalability with respect to the number of robots and types, significantly outperforming MILP-based baselines in both solution quality and computational efficiency.

cs.RO↗

arXiv2026

PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs

Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We present PolyUQuest, a verifiable, structure-aware web RAG framework built on a heterogeneous graph that unifies hyperlink topology between pages, DOM hierarchy within pages, and entity-relation knowledge across pages. A two-tier router dispatches each query to one of three retrieval modes matched to its structural need, including direct block retrieval, cross-page graph traversal, and multi-hop entity reasoning. Each answer carries traceable provenance: every cited block records its source page, heading path, and entity links, so users can inspect the structural evidence behind a claim. We evaluate on the official websites of the Hong Kong Polytechnic University (PolyU), comprising 4,240 pages, 31,086 DOM blocks, 29,119 entities, and 37,680 relations, together with a multi-type evaluation benchmark. PolyUQuest improves correctness, coverage, and faithfulness over the evaluated baselines while maintaining query-time token consumption comparable to ChunkRAG and substantially below the graph-based RAG baselines. The demonstration provides an interactive interface for inspecting cited answers, comparing retrieval traces across routing modes, and exploring evidence graph paths. PolyUQuest is being prepared for deployment as a student-facing QA service at PolyU.

cs.AI↗

arXiv2026

Spine-Branch Coordination for Multi-agent Computer Use

Computer use agents (CUAs) are increasingly deployed as multi-agent systems that decompose a task into multiple subtasks executed across parallel virtual machines (VMs). However, a critical physical bottleneck is that the state of two VMs cannot be merged. Previous systems handle this ad-hoc rather than treating it as a first-class concern. We propose Spine-Branch Coordination for multi-agent computer use, a framework that decomposes a task into a "spine-branch" graph, where the spine carries the main task flow with continuous VM state and branch tasks execute in parallel to collect information the spine needs to complete the task. Branch VMs are discarded once their tasks finish, so no VM merging ever occurs. Experiments show that on 200 long-horizon tasks from Odysseys and across three CUA backbones, Spine-Branch improves success rate over the baseline system by 6.0% to 16.5%, while reducing per-task cost by 34% to 70%, indicating that explicitly modeling VM-state merging constraint enables multi-agent computer use to scale efficiently.

cs.CL↗

arXiv2026

ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks

Computer use agents are evaluated almost exclusively on atomic desktop tasks, but realistic desktop work requires sustaining state across multiple objectives. We study this gap with ChainWorld, which composes atomic OSWorld tasks into long horizon desktop workloads through directional compatibility search while preserving the source evaluators. The resulting workload contains 347 chains of length two to four and compares two renderings of the same task sequence. In single turn evaluation, all tasks are presented together in one prompt. In multi turn evaluation, tasks are revealed one at a time. Across four current computer use agents, maximum chain completion is 31%. Multi turn evaluation improves completion for three models, but both protocols remain challenging. The two protocols also expose different failure profiles. Single turn failures concentrate on artifact precision, while multi turn failures more often reflect session management problems such as fragmented progress and later turn disengagement.

cs.AI↗

arXiv2026

Unlocking Multi-Component Bulk-Materials Molecular Dynamics with a Small-Footprint Machine Learning Interatomic Potential

Bulk materials, as opposed to nanomaterials, require molecular dynamics (MD) simulations on a large spatial scale (~10^9 atoms or more) to adequately capture their atomic-scale physical properties. Previously, the introduction of machine-learning interatomic potentials (MLIPs) has extended MD to this scale, but even single-component bulk systems require tens of thousands of GPUs on high-end supercomputers. However, multi-component bulk MD simulations remain barely achievable, as the HBM footprint of existing MLIPs - already substantial for single-component systems - grows explosively in multi-component scenarios. This paper proposes an MLIP with a small HBM footprint - less than 3% that of existing MLIPs - unlocking multi-component bulk MD using only hundreds of GPUs. This is achieved by first identifying feature vectors and intermediate tensors as the two primary contributors to HBM footprints in existing MLIPs. To address these two sources, the dimensionality of the feature vectors has been reduced by introducing physical and chemical knowledge, and intermediate tensors have been eliminated by aggressively fusing all kernels into a single mega-kernel. In evaluation, the proposed MLIP has used 144 NVIDIA A100 GPUs to perform MD simulations on a 6-component bulk system with 1.14x10^9 atoms, while previously such MD simulation spatial scale has been restricted to unary systems and typically achieved on high-end supercomputers equipped with tens of thousands of GPUs.

physics.comp-ph↗

arXiv2026

High-dimensional Multi-objective Bayesian Optimization with Learned Variable Interactions

Multi-objective Bayesian optimization (MOBO) is effective in identifying the Pareto fronts for expensive black-box problems. However, most current MOBO approaches are limited to low-dimensional decision space due to its exponential sampling complexity. This paper presents decision variable interaction analysis-based MOBO, ViaMOBO, a generic framework for expensive multi-objective problems with high-dimensional decision space. The key idea of ViaMOBO is that it utilizes a variable interaction analysis model to determine whether the decision space can be completely or partially divided, and then performs local Bayesian optimization in the divided decision subspaces. Through the variable analysis model, it can be derived whether the objectives in black-box problems are separable, partially separable, or non-separable based on the potential independent or interdependent relationships among decision variables without any strong assumptions. We compare ViaMOBO with the state-of-the-art MOBO methods on both synthetic and real-world benchmarks. The experimental results demonstrate that ViaMOBO outperforms other related MOBO baselines in approximating the Pareto front of high-dimensional expensive multi-objective problems.

cs.LG↗

arXiv2026

Multi-AUV Ad-hoc network-based Target Tracking: A Value Gradient Guidance Multi-Agent Diffusion Reinforcement Learning Approach

Multi-AUV ad-hoc network-based target tracking requires networked autonomous underwater vehicles (AUVs) to cooperatively track maneuvering targets under constrained acoustic communication, dynamic topology, and uncertain ocean disturbances. Although multi-agent reinforcement learning (MARL) enables decentralized coordination through centralized training, existing methods suffer from high-dimensional joint state-action modeling, noise-sensitive policy generation, leading to unstable training and degraded tracking. To address these issues, we propose VGG-MADiffRL, a value-gradient-guided multi-agent diffusion RL algorithm, and MDCA, a diffusion?based hierarchical control architecture. Leveraging underwater mission characteristics, we model sonar detection mechanisms and ocean current disturbances, formulating cooperative tracking for multi-AUV ad-hoc networks as an MDP. The proposed MDCA constitutes a three-tier closed-loop control framework: a global intelligent control layer, a local online training layer, and a physical action execution layer. This structure enables synergistic optimization across task allocation, local decision processes, and execution feedback. Within MDCA, the local online training layer is the policy learning framework; VGG-MADiffRL builds on diffusion policies and incorporates value gradients to guide action generation in the reverse denoising process, steering the generated actions towards higher expected returns. It employs twin value networks with joint optimization and soft target updates to mitigate overestimation and training oscillations, promoting more stable convergence. Experimental results show that VGG-MADiffRL consistently achieves faster convergence, higher tracking accuracy, and smoother training dynamics in cooperative tracking scenarios, validating its effectiveness and practical engineering value in dynamic underwater settings.

cs.LG↗

arXiv2026

Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge

Enterprise question answering requires models to acquire proprietary knowledge without discarding general capabilities. We present Wnuan, a three-stage pipeline that constructs task-oriented supervision from documents, performs supervised fine-tuning with general-data replay, and applies reinforcement learning to residual errors. On the 707-question WnuanBench, the primary 32B route raises acceptable-answer rate (AAR) from 52.76% before adaptation to 80.06% after SFT and 91.51% after RL. Under a matched 100-update protocol, residual-error sampling outperforms full-pool and size-matched random sampling by 3.11 and 2.97 points, respectively. Source-cluster bootstrap intervals remain above zero for both contrasts, and a same-domain validation set preserves the ordering. The general-benchmark average decreases by 5.17 points across the route, concentrated in instruction following. The automatic evaluation ensemble agrees with an authoritative domain expert on 90.5% of a stratified Wnuan-Inst response sample. These results characterize both the gains and the general-capability cost of staged enterprise adaptation.

cs.AI↗