arXiv subjects

Bowen Liu

Publications and source records attributed to Bowen Liu.

At least 19 recordsLinked to original sources

arXiv2026

SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores

Scientific coding agents produce interdependent code, results, figures, and claims, yet evaluating final outputs alone does not establish whether their conclusions are scientifically supported. We formulate evidence-grounded multimodal scientific analysis, requiring agents to produce executable analyses and claims supported by results and visualizations from the same run. We introduce SciRIGOR, an evaluation framework and benchmark comprising 100 cases from scientific articles across six domains and 17 subfields. The framework reconstructs typed evidence graphs, separates artifact fidelity from relational validity, and scores complete claim-support paths while localizing the earliest unsupported relation. Source-grounded alternative paths accommodate scientifically equivalent analyses and visualizations. We evaluate 11 agent/model configurations. On full-benchmark runs, claims agree with faithful and unfaithful results at nearly identical rates (91.8% versus 91.0%). Yet no system exceeds 62.6% on the soft evidence-chain score or 18.0% strict whole-chain success. These findings show that internal coherence does not establish scientific correctness: evaluation must verify support along the complete data-to-claim path.

cs.AI↗

arXiv2026

An Approach to Study the Structural Consistency of Triangle Badness Functions and Distance Metrics

Triangle-based measures, commonly referred to as badness functions, are widely employed to quantify the extent to which a distance matrix deviates from an ideal geometric configuration. Different formulations of these functions may capture distinct facets of local non-uniformity, and their behavior is often influenced by the underlying distance metric chosen for evaluation. In practical settings, although a canonical badness function may be conceptually preferred, factors such as computational cost, algorithmic constraints, or data-specific characteristics frequently necessitate the adoption of modified versions-for instance, approximate forms or alternatives defined under different distance metrics. This gives rise to a central question: to what degree do these variants retain the structural consistency properties of their original counterparts? To address this issue, we develop a systematic correlation-based framework for evaluating structural consistency. As an illustrative instantiation of this framework, we compute badness sequences from a set of representative distance matrices alongside randomly generated triangle configurations, which are designed to cover variants that may arise under diverse practical scenarios. We then assess pairwise similarities among these sequences using four correlation coefficients. The experimental outcomes indicate that certain badness variants exhibit a notably high degree of structural consistency, whereas others reveal complementary behavioral patterns; moreover, the choice of distance metric exerts a considerable influence on the observed trends. These findings offer practical insights for the informed selection of distance metrics and triangle badness function variants in tasks including geometric reconstruction, triangulation, and structural analysis of pairwise distance data.

math.MG↗

arXiv2026

OVIBench: Benchmarking Online Video Question Answering under Interruption

Recent vision language models (VLMs) have achieved strong progress in video understanding. However, most existing video QA research and benchmarks still follow an offline, single-round paradigm, overlooking realistic interactions where users may interrupt the model during answer generation. To address this gap, we formulate the task of Online Video Question Answering under Interruption and introduce OVIBench, the first standardized benchmark for evaluating VLMs in this setting. OVIBench categorizes interruptions into three types: Cancellation, False Trigger, Correction and supports both open-ended and multiple-choice evaluations. To enable large-scale and reproducible testing, we develop an offline simulation protocol that reproduces interruption during generation under a unified temporal setup, together with a multi-dimensional metric suite for assessing interruption understanding and response generation. Experiments demonstrate that OVIBench effectively distinguishes models' interruption-handling abilities, especially in following correction requests. Finally, we construct a train set OVI-Train for interruption-aware fine-tuning. Models fine-tuned on this dataset achieve significant gains on OVIBench, validating the effectiveness of our benchmark and data design. OVIBench, OVI-Train, and the evaluation code will be released.

cs.CV↗

arXiv2026

PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts

Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-answering benchmarks primarily measure final answer accuracy--a metric vulnerable to linguistic priors and benchmark regularities, and insufficient to establish that predictions are grounded in the supplied tissue. We introduce PathoArgus-Bench, a benchmark and evaluation protocol that explicitly tests the full evidence chain: availability, accessibility, use, and responsiveness. PathoArgus-Bench comprises 22,078 four-choice questions from 4,913 patients across 15 TCGA projects, covering six pathology capabilities across three levels of evidence demand, and operates under a fixed reader budget that retains only a small fraction of the gigapixel context. To further isolate evidence-grounded reasoning, we contribute ESG (Evidence State Quartets), a controlled set of 483 quartets where the question text is fixed while the target WSI set is moved, replaced, or removed, requiring consistent predictions across all states. Evaluating 20 general-purpose, medical, and pathology-specific systems reveals a stark gap: while GPT-5.6 achieves 57.09% overall accuracy and 57.04% on ESG, it correctly completes only 19 of 483 quartets (3.93% QExact), exposing that row-level accuracy does not translate into reliable evidence grounding. We also introduce PathoArgus, a fixed-budget reader that allocates context via question relevance and spatial coverage, attaining 50.39% overall accuracy yet only 1.86% QExact--demonstrating that improved context access alone does not ensure consistent evidence-based prediction. Our benchmark and diagnostics establish that acquiring useful whole-slide context is necessary but far from sufficient, and call for a shift from answer-centric to evidence-grounded evaluation in computational pathology.

cs.CV↗

arXiv2026

MoFE: A Novel Mixture-of-Experts Framework with Fourier Neural Operators for Cryptocurrency Forecasting

Forecasting cryptocurrency prices remains a formidable challenge due to inherent non-stationarity, abrupt regime shifts, and multi-scale stochastic dependencies. Conventional deep learning models often struggle to capture complex underlying dynamics, frequently resulting in persistent phase-lagged predictions. To address these limitations, we propose MoFE, a novel deep learning framework that integrates Fourier Neural Operators (FNOs) within a Mixture-of-Experts (MoE) architecture. Rooted in the theoretical framework of stochastic differential equations, MoFE conceptualizes cryptocurrency volatility as a superposition of multi-frequency components, which includes user network based fundamental growth, mining costs and halving mechanism caused seasonal volatility, and market sentiment-induced chaos. Specifically, specialized adaptive FNO (AFNO) and Convolution dual-domain experts learn continuous function-to-function mappings to encapsulate global spectral trends, cyclical adjustments and microstructures, while a dynamic gating based MoE mechanism enables adaptive strategy switching across diverse market regimes. Extensive experiments on Bitcoin datasets spanning January 2020 to December 2025 demonstrate that MoFE achieves state-of-the-art (SOTA) performance in both T+1 and T+5 forecasting horizons. Notably, the model effectively mitigates the phase-lag effect, delivering superior Directional Accuracy (DA) and Information Coefficient (IC). In high-fidelity simulated trading environments, these predictive gains transfer into significant excess returns and robust risk-adjusted performance, characterized by a high Sharpe ratio.

cs.LG↗

arXiv2026

$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent benchmarks use independent per-task budgets; existing shared-budget studies do not calibrate suite performance against the same model's demonstrated single-problem competence. We introduce $R^3$-Bench, which evaluates six-problem suites under shared budgets across mathematics, competitive programming, and abstract reasoning in tool-free and agentic settings. Matched single-problem response curves define an offline empirical oracle over observed successes. Across 72 main-table cells for six models, the oracle mean matches or exceeds the contest mean in all cells and is strictly higher in 71. Under moderate tool-free pressure, equal-allocation replay also exceeds contest performance for four of six models. Trajectory diagnostics reveal limited strategy updating and pressure-dependent failure patterns. In a three-model diagnostic under strong agentic pressure, at least one fixed scheduler exceeds the contest mean in six of nine cells, but no policy dominates across domains. These results expose a persistent gap between demonstrated competence and shared-budget realization.

cs.CL↗

arXiv2026

CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations

Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints. However, existing evaluations fail to accurately model real network characteristics or assess agents under partially observable telecom environments with diverse vendors, devices, protocols, and interfaces. In this paper, we introduce CTBench, a public benchmark for assessing whether an agent behaves like a competent telecom troubleshooting engineer. CTBench focuses on root cause analysis and path restoration. Each task is constructed by experts and annotated with rich task metadata, including golden evidence steps. CTBench uses expert-grounded metrics that evaluate both final answers and the diagnostic evidence. Experiments with representative harness-model combinations show that state-of-the-art agents perform very well at identifying endpoints in path-restoration tasks but, more generally, underperform in root cause analysis. In particular, agents struggle with interface state, link-layer, service-management, and other operational faults. Most importantly, even when agents produce plausible or correct final answers, they often fail to provide the evidence-grounded diagnoses required in operational practice. Our results further show that path restoration is generally more resource expensive, yet larger resource usage does not necessarily translate into better diagnosis.

cs.AI↗

arXiv2026

Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding

Long-video understanding commonly compresses videos into a small set of frames or visual tokens for answer generation. Existing compact pipelines focus on retaining relevant visual content as explicit evidence. Yet making evidence available does not ensure that complementary cues across moments are integrated for answering. Our key idea is to organize selected frames into query-relevant cross-frame evidence before generation. We formulate this post-selection stage as a latent evidence interface and instantiate it with GenEvA ($\textbf{Gen}erative$ $Latent$ $\textbf{Ev}idence$ $\textbf{A}ggregation$), a distribution-guided latent evidence aggregation framework. Specifically, GenEvA uses a query-conditioned evidence distribution to focus aggregation on relevant frames, forming compact cross-frame latent evidence from their frame-specific information. Since cross-frame integration is not always needed, the same distribution determines whether to insert this latent complement. Across four benchmarks and two Video-MLLM backbones, GenEvA consistently improves matched-frame baselines. At 8 frames, it raises the four-benchmark LLaVA-Video average by $+5.2$ points and Qwen2.5-VL accuracy on LVBench by $+10.1$ points. These gains require only $0.11\%$--$0.40\%$ average video-token overhead; analyses further show task-aware allocation and benefits from Adaptive Evidence Invocation.

cs.CV↗

arXiv2026

Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks

Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by $F_1$, an ``always positive'' policy attains $F_1 = 2\pi/(1+\pi)$; on R-Judge that is $0.690$, above five of the 21 models that actually discriminate. The three broad-coverage benchmarks then rank the same 18 models differently, and the trade-off behind that disagreement is a small-panel artifact: R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n{=}7$ and $+0.02$ at $n{=}18$, and a quarter of random size-7 subsets reach $|\rho| \geq 0.5$ around that near-zero value. Held-out validity turns on which outcome you pick. Capability predicts task success ($\rho{=}{+}0.60$) but correlates negatively with misalignment safety ($\rho{=}{-}0.44$, $n{=}21$). On their paired $n{=}20$ panel, the corresponding contrast is $\Delta{=}{-}1.00$ (95% CI $[-1.48, -0.49]$, $p<0.001$), and it survives leave-one-organization-out and organization-clustered bootstrap analyses. On an expanded 41-model panel, the misalignment correlation weakens to $-0.16$ (95% CI $[-0.54, +0.22]$) and jailbreak strengthens to $+0.34$, though neither change is significant. \mbox{AgentHarm} shows the strongest held-out association, $\rho{=}{+}0.72$ with three-template jailbreak safety after controlling capability. But both instruments score harmful compliance, so this is evidence of convergent validity rather than general safety. Naming the benchmark, metric, target behavior, and model panel is the minimum a safety claim needs.

cs.AI↗

arXiv2026

Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors

Large language model (LLM) tutors may have access to teacher notes, answer keys, rubrics, or retrieved solutions while producing student-facing explanations. We study whether truncated reasoning probes can distinguish direct access to such private context from answer information carried by the written explanation. Using Truncated Reasoning AUC Evaluation (TRACE), we evaluate 1000 GSM8K problems under question-only, correct answer-key, and wrong answer-key contexts. When forced-answer probes retain the private key, answer-key TRACE AUC rises from 0.375 to 0.900, and the gold answer is recoverable with no explanation at all in 998 of 1000 cases. We then introduce a context-masked replay: answer-key-generated prefixes are probed under the corresponding question-only prompt. Masking reduces 10\% prefix accuracy from 0.997 to 0.126 and median AUC from 0.900 to 0.375, nearly matching question-only values of 0.113 and 0.375. On 746 pairs where both explanations end correctly, the masked mean AUC difference is $-0.0086$ with a 95\% bootstrap interval spanning zero. Wrong keys still account for 272 of 387 incorrect final responses, showing that private artifacts can influence outputs even when early-prefix evidence disappears after masking. These results establish context masking as necessary for attributing early answer availability to an explanation rather than its hidden input.

cs.AI↗

arXiv2026

iSTAR: an algebraic-collapse framework for variational reduction in quantum-inspired continuous Ising solvers

Continuous Ising solvers embed a discrete optimization problem into a continuous dynamical system and recover the spin configuration by sign readout, but dense interaction evaluation gives an $O(N^2)$-per-step cost. We show that this cost is not intrinsic: during late-stage simulated bifurcation the trajectory collapses onto a lower-dimensional active subspace, and saturated coordinates can be eliminated exactly by a variational frozen-set identity whose couplings fold into an induced field on the unresolved subsystem. We prove large-parameter recovery for the external-field quartic model, the hard-box limit of ballistic confinement, and a robust-margin freezing criterion. The resulting algorithm, iSTAR (Ising Stable-set Tail-Aware Reduction), exploits this collapse by detecting stabilized coordinates and continuing only on the active tail. An online certified implementation on the G-set benchmark preserves the same-seed baseline in all runs and removes on average 64.4% of the dense interaction work.

math.NA↗

arXiv2026

VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection

Grounding deictic gestures in natural images is fundamental to AR and human-robot collaboration, providing a basis for seamless spatial interaction. While Transformer-based visual models have achieved significant progress in general object detection, their global attention mechanisms often neglect micro-geometric relationships, degrading orientation accuracy. In pointing tasks, this deficiency manifests as an inability to accurately capture the pointing ray implied by finger poses, which results in pointing drift and localization ambiguity when dealing with distant or densely packed objects. To address this, we propose VistaRef, a framework designed to explicitly enhance spatial orientation awareness. First, we develop the Local Hand Entity Modeling (LHEM) module, which incorporates hand-pose embeddings to strengthen the model's capability to capture subtle finger deviations. Second, drawing inspiration from multi-view geometry, we construct the Geometric Ray Modeling (GRM) module to transform implicit orientation information into explicit spatial geometric features, guiding feature aggregation and deep fusion via attention mechanisms. Furthermore, we introduce a novel Orientation-Consistent Alignment Loss (OCAL) to synergistically supervise hand presence and pointing consistency, ensuring that all architectural improvements collectively serve the core objective of spatial localization. Experimental results demonstrate that VistaRef significantly outperforms the baseline, achieving a 14-point absolute gain in grounding accuracy. Qualitative analysis further confirms that VistaRef effectively models the geometric correlation from hand to target, bridging the spatial perception gap inherent in traditional Transformers for complex scenarios. Code: https://github.com/lingli1724/VistaRef.

cs.CV↗

arXiv2026

PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought

Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures. Traditional methods typically encode input images into static feature representations and perform reasoning primarily within the linguistic domain, often overlooking the rich perceptual cues and explicit spatial geometry inherent in images. In this study, we aim to mitigate the cognitive vulnerability of models in interpreting gestural spatial relations by proposing PointVG-R, a reasoning-guided Multi-modal Large Language Model (MLLM). PointVG-R introduces geometric-aware reasoning for pointing-based grounding, enabling the model to think with images through the strategic integration of Reinforcement Learning (RL) and cold-start data. Specifically, we design a novel geometric reasoning pipeline that simulates the iterative cognitive process humans employ when interpreting pointing gestures. Furthermore, we construct EgoPoint-CoT, a high-quality visual Chain-of-Thought (CoT) dataset featuring detailed reasoning trajectories to guide the model via Supervised Fine-Tuning (SFT) and RL. To address the varying quality of learning signals encountered during training, we further propose an Adaptive Importance Weighting strategy based on Group Variance, which dynamically adjusts reward signals to optimize the learning process. Experimental results demonstrate that PointVG-R achieves SOTA performance, outperforming the baseline by $\textbf{15.86}$ points in mIoU. Extensive ablation studies further validate the efficacy of our proposed modules. Code: https://github.com/lingli1724/PointVG-R.

cs.CV↗

arXiv2026

DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics

Post-training quantization (PTQ) is essential for efficient large language model inference, but reliably quantizing activations remains challenging when weights, activations, and KV caches are all quantized to 4-bit precision. A key difficulty lies in massive activations, whose extreme values dominate the activation range and amplify quantization errors. State-of-the-art methods mainly mitigate massive activations through transformation-based smoothing, such as orthogonal rotations and affine scaling, but overlook the cross-layer dynamics of the residual stream. In this paper, we show that massive activations emerge and disappear in a phase-wise pattern across network depth, triggering large residual changes. These changes cause newly injected layer-wise updates to dominate the 4-bit quantization scale and weaken historical residual information. To characterize this behavior, we introduce Jump Ratio and Historical Feature SNR. This suggests that static transformation-based smoothing cannot fully resolve dynamic quantization instability caused by cross-layer residual changes. Based on this analysis, we propose DynamicPTQ, a Dynamic Post-Training Quantization policy for phase-aware mixed-precision activation quantization. DynamicPTQ identifies quantization-sensitive layers from residual-stream dynamics and assigns 8-bit activation precision only to these layers, while keeping weights, KV caches, and other activations in 4-bit precision. It can be directly integrated with strong PTQ baselines such as QuaRot, SpinQuant, and FlatQuant. Experiments on LLaMA-2 and LLaMA-3 show that DynamicPTQ consistently improves perplexity and zero-shot QA performance under W4A4KV4 quantization, while achieving 1.05 to 1.07 times throughput improvement with modest memory overhead. These results demonstrate a practical path toward robust low-bit LLM inference.

cs.LG↗

arXiv2026

See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding

Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods still face two key limitations: evidence acquisition often relies on a single search intent, and answer generation lacks an effective visual feedback mechanism. To address these limitations, we propose \textbf{CoVER}, a Comprehensive Visual Evidence and Reflection framework for long-video understanding. CoVER enables Video-LLMs to \textbf{See More} by dynamically gathering query-expanded visual evidence, and \textbf{Think Deeper} by verifying draft answers with effective answer-specific visual feedback. Together, these mechanisms shift long-video understanding from answer-centric generation to evidence-centric and visually verifiable reasoning. Experimental results show that CoVER-7B substantially outperforms models with the same parameter scale and even surpasses state-of-the-art closed-source models on certain metrics.

cs.CV↗

arXiv2026

A Cryogenic Hybrid Photonic/CMOS Controller Architecture for Scalable Superconducting Qubit Control

Scaling superconducting quantum computers toward thousands of control channels remains a difficult hardware problem. This requires reducing room-temperature-to-cryogenic interconnects and 4 K power while retaining channel-specific programmability. We develop a hybrid photonic/CMOS control architecture in which optical fibers distribute shared Gaussian and derivative pulse templates, while local cryogenic CMOS circuits provide event-rate amplitude programming, pulse blocking, hold-duration control, photodetection, and microwave upconversion. The architecture supports template-based XY/DRAG control and smooth-edged flat-top envelopes for two-qubit control through separate local signal paths. Compared with full-waveform Cryo-CMOS, it moves high-speed sampled-waveform generation out of each cryogenic channel. Compared with per-channel photonic waveform delivery, it retains a programmable endpoint after optical distribution for applying updated channel coefficients and control states. We evaluate the architecture using post-layout circuit simulations, optical and interconnect models, and system-level power scaling under a common 4 K output boundary. The modeled downlink power is below 1 mW per qubit-control channel at the thousand-channel scale, substantially below the normalized full-waveform Cryo-CMOS result and in the same range as the strict 50-ohm direct-detection WDM reference. Simulated I- and Q-path outputs are propagated through a five-level transmon model, while the simulated sample-and-hold output is evaluated in a coupled-transmon model. The tested single-qubit cases remain below the 10^-3 worst-state error reference, and the representative two-qubit result remains near the same scale after model-level calibration. These results support low-power photonic delivery with limited in-fridge programmability for template-compatible superconducting-qubit control.

quant-ph↗

arXiv2026

When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL

For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test. Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding -- plus a rarer weak-shaping case. We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision. Refinement improves DoorKey-8x8 from 2.3% to 97.6% and KeyCorridor from 31.2% to 86.7% with high seed-to-seed variance. Controls show these gains are not from retrying or extra training: metrics-only re-prompting yields large drops, while a static-vocabulary control recovers much of the gap (87.6%; 70.7%), showing the taxonomy prompt is a major mechanism and dynamic labels provide only partially isolated incremental evidence. Budget-matched and Best-of-3 comparisons separate refinement from selection and training-time effects. Component-removal tests, sensitivity analyses, and an audit against author labels provide converging evidence for the debugging interpretation while revealing calibration limits. Continuous-control results show the boundary: success-based diagnostics can misfire in dense-reward locomotion, and return-trend feedback removes one false-positive mechanism without robust gains. The low-call protocol is a cost contrast with population-based reward search, not a benchmark comparison. In four crossed-variance-design environments, point estimates suggest larger gains when LLM reward-function variance dominates but bootstrap intervals are wide. The method is bounded to sparse structured tasks with reliable interfaces under PPO; fields like event_text may help, hurt, or be neutral.

cs.LG↗

arXiv2026

CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP solver and which mechanisms govern the gains. We model feedback-driven solving as a calibrated stopped process and identify three quantities: false-admission risk, program-level evidence against bad programs, and the active-state success hazard. Under held-out trace calibration and selection from a pre-declared finite controller manifest, the resulting structural certificate lower-bounds the clean success probability before false admission. We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent. Without updating any parameters, CP-Agent raises Pass@1 from 25.8\% to 48.5\% on LiveCodeBench Pro and improves Refine@5 by 11.0\% on ICPC-Eval. Across three LLM backbones, CP-Agent lies on the cost--accuracy efficiency frontier, and ablations show that each component primarily affects its corresponding certificate quantity.

cs.CL↗