Searcharxiv⌕ Search

arXiv subjects

Bo Chen

Publications and source records attributed to Bo Chen.

At least 73 records · Page 4Linked to original sources
arXiv2026

Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection

LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors, schema mismatches, and heterogeneous page structures. We propose a constrained, verifiable agent framework that shifts LLM output from free-form code to typed JSON collector configurations, combining a six-type collector taxonomy, template and utility-function constraints, static Airflow DAG execution, rule-based quality checking, and structured feedback correction. Experiments on 138 tasks show that the taxonomy supports description-based requirement typing, while confirming that stable instantiation requires completing source, field, and execution constraints beyond the initial description. On 80 independently source-verified tasks, the framework runs with zero execution-stage LLM tokens and the lowest average wall-clock time, trading moderate one-shot quality for a reusable, deterministic, and verifiable execution path suited to repeated scheduled collection. These results position the framework as a reusable, low-cost, and verifiable execution path for repeated open-web data collection.

cs.AI↗
arXiv2026

When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance

Can a statistically significant, large-effect-size finding in computational social science be entirely an artifact of the measurement instrument? We present a case where the answer appears to be yes. Analyzing 85 interviews across four public intellectuals (2016--2026), we find a robust negative-affect/emphatic-certainty lexical co-occurrence pattern under keyword-based scoring ($r = 0.72$--$0.93$, $p < 0.01$ for all four speakers). Replacing keyword counting with LLM-based zero-shot semantic classification on the complete diarized corpus (32,625 sentences) dramatically reduces this correlation: Dalio's $r = 0.851$ drops to $r = 0.206$, with two speakers showing negative $r(\text{neg}, \text{emphatic})$ and one showing null. In contrast, the LLM reveals a strong negative-hedging coupling across speakers -- Rogoff's $r(\text{neg}, \text{hedged}) = 0.875$ ($p = 0.001$) and Zeihan's $r(\text{neg}, \text{hedged}) = 0.722$ ($p = 0.008$) -- consistent with the conventional expectation that pessimistic discourse attracts hedging, not certainty. Sentence-level error analysis traces this discrepancy to three structural failure modes in keyword lexicons -- syntactic blindness, polysemy blindness, and categorical absence -- illustrated through cases where keyword counting inverts semantic meaning (e.g., ''never absolutely totally confident'' scored as high-certainty). We argue that keyword lexicons measure a universal lexical co-occurrence tendency -- negative discourse naturally attracts emphatic vocabulary -- that is orthogonal to, and can systematically invert, rhetorical stance. Treating keyword counts as measurements of epistemic certainty is a category error: a finding that appears to be about a speaker's psychology may be entirely about the counting of words.

cs.CL↗
arXiv2026

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

cs.AI↗
arXiv2026

Maximum Utility Split Method for Utility Preference Elicitation

In this paper, we propose a new approach, called maximum utility split (MUS) scheme, which is built on random utility split (RUS) scheme but with a notable difference: one lottery is designed with two fixed outcomes but with varying probability, and the other has a deterministic outcome specifically chosen at the point where the range between the largest and smallest possible utility values is maximized. Consequently, the probability of random lottery is set such that the range of the ambiguity set of utility functions is reduced by half at the point. Under moderate conditions, we show that MUS can successively generate a sequence of such questionnaires and effectively reduce the ambiguity set, eventually converging to the true utility function as the number of questionnaires increases. The main challenge is to effectively identify the point with the largest utility range for a given ambiguity set constructed from preference information. Based on the structure of the ambiguity set, we propose an interval-based algorithm which identifies each certain-outcome lottery by solving a sequence of linear programs. Moreover, to deal with the case where elicitation terminates before the ambiguity set reduces to a singleton, we demonstrate how to figure out a nominal utility function by solving optimization programs. These identify the smallest and largest utility functions under the Kantorovich metric within the ambiguity set, after which we identify a nominal utility function located in the middle of them. Finally, numerical results demonstrate the efficiency of the MUS method and the performance of a robo-advisor system based on MUS-type queries and the nominal utility elicitation. While the main discussions focus on concave utility functions, we also demonstrate how the MUS approach can be extended to accommodate general non-concave utility functions, particularly S-shaped ones.

math.OC↗
arXiv2026

HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation

World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantly enhance generalization and robustness. However, existing WAMs still struggle with task-relevant memory in long-horizon robotic manipulation. To address this, we present HiMem-WAM, a Hierarchical Memory-Gated WAM that integrates motion-centric latent actions, high-level skill latents, and boundary-triggered memory updates. Specifically, we develop a hierarchical latent action framework that jointly learns low-level motion and high-level skill latents, providing structured temporal abstraction. Meanwhile, a boundary-aware memory gate writes compact task states at predicted skill transitions, enabling causal inference without test-time generation of future video or optical flow estimation. Evaluated on LIBERO, LIBERO-PLUS, RMBench and real-world tasks, HiMem-WAM shows that hierarchical latents improve robustness under deployment perturbations, and the memory module substantially benefits memory-dependent long-horizon manipulation.

cs.RO↗
arXiv2026

Cross-Source Reasoning-based Correction for Author Name Disambiguation

Author name disambiguation is a critical challenge in academic search systems, often addressed through from-scratch and real-time disambiguation approaches. However, current algorithms remain vulnerable to cumulative errors of paper-author assignments and overlook inconsistent assignments across different sources. Resorting to expert annotation is resource-intensive. To this end, this paper explores a new perspective for author name disambiguation: cross-source correction by leveraging inconsistent assignments across sources. We propose CrossND, a full-stack framework that integrates data refinement, cross-source reasoning, and test-time scaling. First, a chain-of-refinement pipeline denoises author profiles and produces more accurate paper-author matching probabilities. Second, a supervised fine-tuning process incorporates these refined signals and a probabilistic soft logic-based cross-correction module to infer the assignments of which sources are incorrect. Third, test-time scaling further enhances the accuracy and robustness of the predictions. Experiments on real-world datasets indicate that CrossND consistently outperforms 17 baselines by leveraging cross-source reasoning without human intervention.

cs.CL↗
arXiv2026

Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling

Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet they are often vulnerable to reward hacking due to noisy annotations and systematic biases such as response length or style. We propose Bayesian Non-Negative Reward Model (BNRM), a principled reward modeling framework that integrates non-negative factor analysis into Bradley-Terry (BT) preference model. BNRM represents rewards through a sparse, non-negative latent factor generative process that operates at two complementary levels: instance-specific latent variables induce disentangled reward representations, while sparsity over global latent factors acts as an implicit debiasing mechanism that suppresses spurious correlations. Together, this disentanglement-then-debiasing structure enables robust uncertainty-aware reward learning. To scale BNRM to modern LLMs, we develop an amortized variational inference network conditioned on deep model representations, allowing efficient end-to-end training. Extensive empirical results demonstrate that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.

cs.LG↗
arXiv2026

Deep Research as Rubric for Reinforcement Learning

Open-ended reasoning and long-form generation tasks lack reliable automatic verification signals for reward-based policy optimization. Rubrics offer a promising alternative, but existing approaches treat them as given artifacts -- either hand-crafted or prompt-generated -- and often miss the task-specific, knowledge-intensive dimensions that matter most, distorting the reward signal. Our key observation is that rubric construction is itself a research problem: identifying what makes a response correct or insightful requires discovering and synthesizing external knowledge. We propose Deep Research as Rubric (DR-rubric), a two-stage framework for constructing such rubrics. Stage I elicits domain facts, structural constraints, and failure modes through iterative multi-turn agentic search; Stage II distills this evidence into atomic, independently verifiable constraints for GRPO-based policy optimization. Because the model under training can serve as its own rubric generator, DR-rubric-8B supports bootstrap rubric generation without frontier-model assistance. We evaluate on 6 benchmarks spanning agentic research and expert reasoning. Experiments show that DR-Rubric achieves strong competitive performance with only 1K -- 3K training instances, where GPT-5-generated rubrics particularly benefit breadth coverage on agentic tasks, Gemini-generated rubrics yield the most balanced performance across agentic and expert reasoning tasks, and bootstrap rubrics exhibit a specialization-to-rebalancing evolution achieving the best overall performance at the third iteration. Results demonstrate that reframing rubric construction from static evaluation templates into an evidence-driven research process yields more scalable, fine-grained reward signals for open-ended tasks.

cs.CL↗
arXiv2026

Electronic Nematicity Revealed by Polarized Ultrafast Spectroscopy in Bilayer La$_3$Ni$_2$O$_7$

We report a polarized ultrafast pump-probe study of the normal-state electronic dynamics in bilayer La$_3$Ni$_2$O$_7$ and trilayer La$_4$Ni$_3$O$_{10}$ single crystals at ambient pressure. While both nickelates exhibit density-wave (DW) transitions accompanied by the opening of a quasiparticle relaxation bottleneck, their electronic responses display strikingly different symmetry properties. La4Ni3O10 maintains an isotropic optical response across the entire temperature range. In contrast, La$_3$Ni$_2$O$_7$ exhibits a pronounced twofold ($C_2$) anisotropy in its lowtemperature electronic dynamics. This electronic nematicity, evident in both the relaxation dynamics and the polarization-dependent effective bottleneck energy scales, is strongly modified below 115 K, suggesting coupling or competition with a secondary DW-like instability reported by complementary probes. The presence of macroscopic electronic anisotropy in the bilayer system, and its absence in the trilayer system, suggests a possible relation between electronic nematic correlations and the superconducting normal state in a$_3$Ni$_2$O$_7$ that deserves further exploration.

cond-mat.str-el↗
arXiv2026

DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve high-precision retrieval, they face inherent limitations. First, the coarse-grained nature of dense embeddings tends to obfuscate explicit semantics, failing to leverage structurally salient information. Second, supervised reranking models suffer from generalization bottlenecks, as their performance heavily relies on domain-specific training data. Furthermore, existing benchmarks often lack diverse assessment dimensions and comprehensive relevance annotations, limiting reliable evaluation. To address these challenges, we propose DocRetriever, a plug-and-play framework. It enhances visual retrieval via a layout-aware sparse embedding technique, enabling effective hybrid encoding without the overhead of optical character recognition (OCR). We also introduce a generalizable reranker that leverages reasoning-augmented demonstrations and optimized sampling to improve accuracy in few-shot settings. Finally, we construct a new benchmark, MultiDocR, to enable more rigorous evaluation. Experiments across diverse benchmarks validate DocRetriever's superiority over state-of-the-art methods.

cs.CV↗
arXiv2026

SurgRFO: Foundation Model Based Compositional Synthesis of Critical Retained Foreign Objects in Intraoperative Chest X-rays

Critical retained foreign objects (RFOs) on intraoperative chest radiographs are rare but high-risk events. Their scarcity limits robust automated detection model training and generalization. We introduce SurgRFO, a two-stage synthesis framework for generating realistic RFO-present intraoperative chest X-rays. In Stage 1, a Roentgen chest X-ray foundation model is fine-tuned on surgical-domain images to generate realistic RFO-free backgrounds that preserve anatomy, indwelling lines and tubes, and intraoperative imaging characteristics. In Stage 2, a lightweight generator trained on localized RFO patches from limited positive cases synthesizes diverse RFO instances, which are composited onto generated backgrounds using conditional Poisson fusion to improve photometric consistency. We evaluate SurgRFO through (i) a blinded clinician study assessing realism and clinical plausibility, and (ii) downstream detection experiments in which synthesized data are used to augment Faster R-CNN, YOLOv8, and RetinaNet. SurgRFO consistently improves sensitivity at low false-positive-per-image (FPPI) operating points on internal and external test sets. Clinician ratings indicate that the synthesized images achieve realism comparable to real intraoperative images. Ablation analyses further examine fusion strategies and synthesis scale. Ethical safeguards for synthetic surgical data are also discussed.

eess.IV↗
arXiv2026

Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces

Multi-class anomaly detection aims to build unified models across diverse product categories. However, as the number of categories grows, its performance often degrades due to increasingly complex and heterogeneous normal distributions. To address this challenge, we propose DPDiff-AD, a Dual Prototype-conditioned Diffusion model for large-scale multi-class Anomaly Detection. DPDiff-AD models heterogeneous normal distributions through complementary local and global prototypes. Local prototypes capture representative fine-grained structural patterns via nearest-prototype aggregation, while global prototypes regulate holistic feature geometry through optimal transport regularization. Together, these dual-scale representations define a structured normality space. This space is refined through diffusion-based reconstruction conditioned on both local and global prototypes via prototype-aware attention. By jointly leveraging dual prototypes during generation, DPDiff-AD achieves precise normality modeling, preserves structured separability as category cardinality grows, and enables scalable anomaly discrimination. Extensive experiments across five benchmarks demonstrate the effectiveness and scalability of DPDiff-AD. On the 160-category large-scale dataset, it improves image- and pixel-level AUROC by 5.3 and 2.9 points over the previous state-of-the-art method Dinomaly+, while maintaining stable performance as category cardinality increases.

cs.CV↗
arXiv2026

Long-horizon prediction of three-dimensional wall-bounded turbulence with CTA-Swin-UNet and resolvent analysis

Long-horizon prediction of three-dimensional (3D) wall-bounded turbulence with machine-learning methods remains a challenging task, due to the rapid accumulation of autoregressive errors and the substantially computational cost. To address these challenges, we present a hybrid machine-learning framework, in which a channel-time-attention Swin-UNet (CTA-Swin-UNet) and a multi-time-scale fusion correction (MTFC) strategy are developed to predict the turbulent flow fields in a wall-parallel plane, with affordable computational cost. Then, 3D flow fields are reconstructed via a resolvent-based spectral linear stochastic estimation (SLSE), rooting from the predicted planar flow. Results show that the CTA-Swin-UNet outperforms the baseline models (LSTM, FNO and traditional Swin-UNet) in both single-step prediction and autoregressive rollouts, indicating the effectiveness of introducing the CTA module into the Swin-UNet architecture. At the same temporal interval, the CTA-Swin-UNet remains stable for approximately 150 rollout steps, while the baseline models fail within 20 to 50 rollout steps. After introducing the MTFC strategy, a longer horizon upto 300 steps is achieved. Using the resolvent-based SLSE reconstruction further recovers the 3D flow structures and energy spectral distributions from the predicted planar inputs, which demonstrates that the proposed framework provides an effective and computationally efficient approach for long-horizon autoregressive prediction of 3D wall-bounded turbulence.

physics.flu-dyn↗
arXiv2026

Benchmarking Real-Time Question Answering via Executable Code Workflows

Retrieving real-time information is a fundamental capability for search-integrated agents in real-world applications. However, existing benchmarks are predominantly static and therefore fail to capture the temporal dynamics of information and the continuously evolving nature of real-world knowledge. To address this limitation, we propose RT-QA, a dynamic evaluation framework that leverages executable code workflows to retrieve up-to-date answers at evaluation time. Specifically, we construct an agent-driven pipeline that autonomously generates code for web crawling and DOM-based answer extraction to produce real-time ground truth. To ensure robust evaluation over time, the pipeline further incorporates a self-repair mechanism to adapt to changes in web page structures. RT-QA spans 12 domains (e.g., Finance, Sports) with 320 Chinese questions categorized into three difficulty levels. Extensive evaluations of state-of-the-art models (e.g., GPT-5.2, GLM-4.7) reveal significant limitations in real-time adaptability: even the best models achieve only 46% accuracy. Our analysis highlights two primary failure modes: (1) Lazy Retrieval, where agents rely on search snippets instead of deeply scanning specific websites for information (20% of failures); and (2) Temporal Confusion, a cognitive error where agents retrieve a historical date (e.g., an event in 2024) and fail to re-anchor to the current time (2026) for subsequent reasoning. These findings suggest that future agents require not just better retrieval strategies, but robust temporal state management.

cs.IR↗
arXiv2026

HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model

Humanoid robots show promise for complex whole-body tasks in unstructured environments. Although Human-Object Interaction (HOI) has advanced, most methods focus on fully actuated objects rigidly coupled to the robot, ignoring underactuated objects with independent dynamics and non-holonomic constraints. These introduce control challenges from coupling forces and occlusions. We present HAIC, a unified framework for robust interaction across diverse object dynamics without external state estimation. Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history. These predictions are projected onto static geometric priors to form a spatially grounded dynamic occupancy map, enabling the policy to infer collision boundaries and contact affordances in blind spots. We use asymmetric fine-tuning, where a world model continuously adapts to the student policy's exploration, ensuring robust state estimation under distribution shifts. Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks (skateboarding, cart pushing/pulling under various loads) by proactively compensating for inertial perturbations, and also masters multi-object long-horizon tasks like carrying a box across varied terrain by predicting the dynamics of multiple objects.

cs.RO↗
arXiv2026

Disentangled Generative Graph Representation Learning

Recently, generative graph models have shown promising results in learning graph representations through self-supervised methods. However, most existing generative graph representation learning (GRL) approaches rely on random masking across the entire graph, which overlooks the entanglement of learned representations. This oversight results in non-robustness and a lack of explainability. Furthermore, disentangling the learned representations remains a significant challenge and has not been sufficiently explored in GRL research. Based on these insights, this paper introduces DiGGR (Disentangled Generative Graph Representation Learning), a self-supervised learning framework. DiGGR aims to learn latent disentangled factors and utilizes them to guide graph mask modeling, thereby enhancing the disentanglement of learned representations and enabling end-to-end joint learning. Extensive experiments on 11 public datasets for two different graph learning tasks demonstrate that DiGGR consistently outperforms many previous self-supervised methods, verifying the effectiveness of the proposed approach.

cs.LG↗
arXiv2026

CPI-C: Cool Planet Imaging Coronagraph on Chinese Space Station Survey Telescope

Cool Planet Imaging Coronagraph (CPI-C) on Chinese Space Station Survey Telescope (CSST) is proposed to direct image the cool planets around nearby solar-type stars (within 40 pc). The core scientific objective of CPI-C is to conduct high-contrast directly imaging surveys of exoplanets ranging in size from Neptune-like to Jupiter-like, located at separations of 0.5 to 5 AU from their host stars, and to perform systematic spectroscopic analysis of the detected planets through high-precision multi-band photometry. CPI-C employs a step-transmission apodization technique to suppress the diffraction noises from the telescope pupil and a precise phase correction technique to eliminate the speckle noises due to imperfections of the optical surfaces. The contrast requirement is better than $10^{-8}$ at an inner working angle (IWA) of $3-4λ/D$, in the visible wavelength from 600 nm to 900 nm. CPI-C will be the first space-based instrument capable of directly imaging the reflection light from the cool exoplanets in the visible wavelength enabling the measurement of key physical parameters such as the effective temperature, surface gravity, radius, mass, and other key parameters. The potential observation results will significantly contribute to further understand the formation and evolution mechanisms of planets, which will also lay a solid foundation for future confirmation of the Earth-twins in the next generation space flagship missions.

astro-ph.EP↗