Searcharxiv⌕ Search

arXiv subjects

Xinyuan Wang

Publications and source records attributed to Xinyuan Wang.

At least 19 recordsLinked to original sources
arXiv2026

Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI

Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the data lifecycle that governs how agents are trained, evaluated, and deployed. Observational interaction logs record what an agent did, not what it would have done otherwise. They encode spurious correlations without controlled variation, so they lack the counterfactual structure needed to separate causal signal from coincidence or to validate an explanation. No model-centric method can recover invariances the data never contained. We present Data-Centric Anchoring: robustness and interpretability should be engineered into the data environment, not extracted from models after training. Our central contribution is the Data-Centric Agentic Loop, a four-stage framework of Curate, Augment, Constrain, and Attribute. The ordering is structural, not stylistic. Curation precedes augmentation because generative models amplify whatever bias they are trained on. Augmentation precedes constraint because invariance objectives are vacuous without variation across environments to be invariant to. Attribution closes the loop, converting observed failures into targeted data interventions for the next iteration. Each stage manufactures the preconditions of the next, which makes the loop self-correcting rather than merely sequential. We ground the framework in a failure-driven taxonomy that links four core failure modes to the data lifecycle: spurious feature reliance, distribution-shift fragility, uncertainty miscalibration, and explanation unfaithfulness. We close with the limits of this approach and the open problems that stand between it and practical deployment at scale.

cs.AI↗
arXiv2026

SkinSpline: A Body-Attached Skeleton-Supported Haptic Interface for Continuous Skin Deformation through Physical Interpolation

We present SkinSpline, a body-attached skeleton-supported haptic interface that renders continuous skin deformation through physical interpolation of sparse mechanical actuation. SkinSpline combines a low-resolution array of rack-and-pinion linear actuators with an elastic interlocking skeleton that transforms discrete actuator motions into smooth surface deformation, enabling continuous cutaneous feedback without dense actuator arrays. The system includes a modular hardware architecture, a configurable control pipeline, and a visual interface supporting real-time configuration and actuation. We demonstrate SkinSpline through multiple scenarios, including wave rendering, video-synchronized rhythmic touch, visually driven water-wave feedback in VR, and sensor-based remote touch reproduction. SkinSpline explores an alternative approach to continuous on-body haptic rendering by leveraging structural coupling between sparse actuation and deformable surfaces.

cs.HC↗
arXiv2026

CSPF: A Constrained Shared-Private Fusion Method for Non-Verifiable Preference Evaluation

At present, reliable evaluation of non-verifiable tasks remains challenging. Existing approaches often fail to adequately capture the diverse evaluative criteria underlying human preferences in such tasks. To this end, we propose Constrained Shared-Private Fusion (CSPF), a fusion method that treats heterogeneous frozen reward models as complementary evaluators and learns to integrate their hidden-state representations under pairwise human-preference supervision. CSPF decomposes each expert signal into shared and expert-private representations, encouraging cross-expert alignment while preserving complementary viewpoints. Across experiments on LM-Arena target-domain adaptation and PPE out-of-distribution preference evaluation, CSPF achieves the best performance on the primary metrics among the evaluated single-expert reward-model, scalar-score multi-expert, and rubric-judge baselines. Overall, CSPF suggests that fusing hidden-state representations provides a more expressive basis for preference assessment, offering a practical route toward integrated evaluative signals for non-verifiable preference tasks.

cs.CL↗
arXiv2026

FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents

Agentic Reasoning has become a transformative force in financial analysis due to its ability to integrate large-scale information and generate reliable and accurate content. However, when handling complex real-world problems, different agents still show significant performance variation. In this work, we design Finance-LaTeX SKILL, a skill for synthesizing financial documents with complex layouts based on expert knowledge. Using an agent workflow built on this skill, we generate 2,000 professional financial documents along with 6,000 high-quality question-answer pairs. To evaluate the overall capability of agents, we introduce FinanceComplexQA, a comprehensive open-ended generation benchmark for financial documents that closely resembles real-world scenarios. It contains 2,026 deep research tasks targeting 1009 financial documents. FinanceComplexQA has 8 key features: bilingual support; coverage of six mainstream scenarios and seven tasks; expert-level document reasoning questions; deep research of complex layouts; relatively stable and permanent reference answers; and precise evaluation through an Agent-as-a-Judge with multiple evaluation metrics. Using FinanceComplexQA, we conduct a comprehensive evaluation of leading RAG systems and agentic reasoning tools for financial document QA. Through identifying and analyzing failure cases, we provide an in-depth study of their capabilities in numerical computation, multi-hop reasoning, content summarization, and industry analysis.

cs.CE↗
arXiv2026

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, designed to capture complex and challenging real-world phenomena. Each task represents a realistic end-to-end workflow that takes human users a median of about 1.6 hours to complete and requires an average of 318 tool calls with Claude Opus 4.7 using maximum thinking, compared with about 30 in OSWorld 1.0. OSWorld 2.0 targets challenge phenomena that are common in real workflows yet underrepresented in prior benchmarks, spanning interaction-design challenges such as streaming interaction and dynamic environments, as well as agent-pattern challenges such as cross-source reasoning, implicit-state inference, and visual-spatial precision. Tasks are grounded in authentic input artifacts and cross-referenced against realistic stateful user profile data, and include separate safety reports auditing safety-sensitive execution. Under our primary binary-completion metric at 500 steps, Claude Opus 4.8 with maximum thinking and batched tool calls scores best but still completes only 20.6% of tasks at a 54.8% partial score; GPT-5.5 is far more token-efficient yet plateaus near 13%. These results show that current agents are still far from professional-level computer use: rather than stumbling on basic GUI control or coding, they lose track of constraints, miss information that arrives mid-task, guess rather than ask the user, and skip verification, struggling most when a task hinges on hidden state they must recover.

cs.AI↗
arXiv2026

PhoneBuddy: Training Open Models for Agentic Phone Use

Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matters at deployment, real devices running real apps, is slow, stateful, side-effectful, and hard to reset or verify, while scalable mock environments only approximate real behavior. We present PhoneBuddy, a training recipe and open-model line for agentic phone use that combines a real-app environment with a mock-app environment, PhoneWorld, which reconstructs runnable mock apps from real GUI usage structure. PhoneBuddy first builds a shared supervised fine-tuning stage from trajectories collected in both environments, then compares real-app RL against mixed RL across both environments. Across a 150-task human evaluation on real phones spanning apps, mini-apps, and cross-app workflows, task success rate improves from 36.67\% after supervised fine-tuning to 40.67\% after real-app RL and 45.33\% after mixed RL. On AndroidWorld, the same progression rises from 60.3\% to 77.2\% to 83.2\%. These results show that mock-app training is not a replacement for real-app RL, but a complementary source of scalable, resettable, and automatically checked interaction. The gains are strongest on app and mini-app tasks, while long-horizontal cross-app workflows remain an important open challenge.

cs.CL↗
arXiv2026

Retrieval-Augmented Multimodal Learning for Enzyme-Substrate Interaction Prediction Under Low-Homology Shift

Enzyme substrate interaction (ESI) prediction is a fundamental computational task for biocatalyst discovery and reaction screening in large biochemical spaces. In practical settings, ESI prediction is challenged by sparse positive supervision and low-homology distribution shift, where test enzymes share limited sequence identity with those observed during training. To address these challenges, we propose RAMMESI, a retrieval-augmented multimodal framework for robust ESI prediction. RAMMESI learns explicit pairwise enzyme-substrate representations through directional cross-modal interaction modeling and adaptive fusion. To enhance robustness, RAMMESI retrieves neighboring enzymes at inference time, recombines them with the query substrate, and aggregates the resulting pairwise predictions as contextual evidence. To improve learning under sparse positive supervision, we further adopt an imbalance-aware weighted-BCE objective. Experiments on two ESI benchmarks under sequence-identity-aware splits demonstrate that RAMMESI achieves consistently strong performance, with particular advantages in more challenging low-identity regimes. In addition, the retrieval module improves multiple ESI backbones in a plug-and-play manner, suggesting that retrieval provides a general mechanism for improving robustness under homology shift.

cs.LG↗
arXiv2026

GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?

Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional coding tasks, game generation takes place within a game engine, where scripts, scenes, assets, rendering, and runtime interactions must jointly produce coherent gameplay. We formalize end-to-end game generation as the problem of producing a complete game artifact that realizes a specification through observable player-game interaction in a target environment. We argue that evaluating this setting requires three desiderata: Engine Grounding, Artifact Completeness, and Interactive Verification. We propose an interaction-grounded evaluation framework that assesses executable gameplay through replayed demonstrations and rubric-guided multimodal judging. We instantiate this framework as GameCraft-Bench, a benchmark comprising 140 Godot tasks across 15 game families. Evaluations of frontier coding agents show that end-to-end game generation remains highly challenging: the strongest agent achieves only 41.46%, and most agents score below 40%. Further analysis reveals that while agents often implement recognizable mechanics, they struggle to deliver complete games with sufficient content, functional visual feedback, and coherent presentation. See https://tongxuluo.github.io/gamecraft-bench-website for demos, code, and data.

cs.CL↗
arXiv2026

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval

Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansion with retrieval decisions in short-horizon inference loops, leading to high inference cost and limited suitability for time-sensitive news retrieval. We propose DynaTree, a two-stage framework for efficient and adaptive news retrieval. In the offline stage, DynaTree uses coordinated agents to construct a reusable retrieval tree that materializes the semantic space of a query topic. In the online stage, DynaTree performs lightweight daily subtree selection over a time-localized evaluation proxy, without further agentic reasoning, tree modification, or retraining. Experiments on a multi-day Syft news benchmark and multiple BEIR datasets show that DynaTree achieves strong recall and ranking performance, consistently outperforming standard RAG and prior agentic baselines. We further deploy DynaTree in the Syft production system and evaluate it through online A/B testing from Jan. 28 to Feb. 6, 2026. The dynamically adapted variant improves survival rate from 0.32-0.53 to 0.59-0.73 over a fixed offline-selected subtree and outperforms existing production recallers on every evaluation day. These results show that persistent, structure-aware semantic expansion can translate offline agentic reasoning into practical improvements in coverage, freshness, and relevance for real-world news retrieval.

cs.IR↗
arXiv2026

PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models

Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generation as sequence generation. Adapting LLMs to web-scale WPO, however, remains bottlenecked by the need for costly human annotations and by the mismatched granularity between page-level coherence and item-level placement. In this work we show that these two challenges are coupled: implicit user feedback alone suffices for alignment, provided the reward signal is decoupled into two complementary granularities. We propose PageLLM, a reward-based fine-tuning framework that (i) turns implicit feedback into four contrastive preference-pair families covering relevance, ranking, diversity, and redundancy, (ii) learns a coarse page-level reward and a fine item-level reward that captures engagement-sensitive position swaps, and (iii) combines both rewards in PPO-based RLHF over a pre-trained LLM. Extensive experiments on seven Amazon categories against eleven baselines show that neither reward alone is sufficient -- dropping the page-level or item-level signal reduces NDCG@100 by 17.8% and 15.2% respectively, whereas the joint reward improves NDCG@100 by up to 46.8%. Deployed in a 10M-user online A/B test, PageLLM raises GMV by 0.44% and click-through rate by 0.14%, confirming that multi-grained rewards from implicit feedback scale to production WPO. Code and data are available at an anonymized repository.

cs.LG↗
arXiv2026

Towards reconstructing experimental sparse-view X-ray CT data with diffusion models

Diffusion-based image generators are promising priors for ill-posed inverse problems like sparse-view X-ray Computed Tomography (CT). As most studies consider synthetic data, it is not clear whether training data mismatch (``domain shift'') or forward model mismatch complicate their successful application to experimental data. We measured CT data from a physical phantom resembling the synthetic Shepp-Logan phantom and trained diffusion priors on synthetic image data sets with different degrees of domain shift towards it. Then, we employed the priors in a Decomposed Diffusion Sampling scheme on sparse-view CT data sets with increasing difficulty leading to the experimental data. Our results reveal that domain shift plays a nuanced role: while severe mismatch causes model collapse and hallucinations, diverse priors match or exceed well-matched but narrow priors. Forward model mismatch pulls the image samples away from the prior manifold, which causes artifacts but can be mitigated with annealed likelihood weight schedules that also increase computational efficiency. Overall, we demonstrate that performance gains do not immediately translate from synthetic to experimental data, and future development must validate against real-world benchmarks.

cs.CV↗
arXiv2026

R^2-Mem: Reflective Experience for Memory Search

Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing deep search agents for memory system repeat past error behaviors because they fail to learn from the prior high- and low-quality search trajectories. To address this limitation, we propose R^2-Mem, a reflective experience framework for memory search systems. In the offline stage, a Rubric-guided Evaluator scores low- and high-quality steps in historical trajectories, and a self-Reflection Learner distills the corresponding abstract experience. During the online inference, the retrieved experience will guide future search actions to avoid repeated mistakes and maintain high-quality behaviors. Extensive experiments demonstrate that R^2-Mem consistently improves both effectiveness and efficiency over strong baselines, improving F1 scores by up to 22.6%, while reducing token consumption by 12.9% and search iterations by 20.2%. These results verify that R^2-Mem provides a RL-free and low-cost solution for self-improving LLM agents.

cs.CL↗
arXiv2026

From History to State: Constant-Context Skill Learning for LLM Agents

Large language model (LLM) agents are increasingly used to operate browsers, files, code and tools, making personal assistants a natural deployment target. Yet personal agents face a privacy-cost-capability tension: cloud models execute multi-step workflows well but expose sensitive intermediate context to external APIs, while local models preserve privacy but remain less reliable. Both settings also pay repeatedly for long skill prompts and growing histories. We propose constant-context skill learning, a context-to-weights framework for recurring agent workflows: reusable procedures are learned in lightweight task-family modules, while inference conditions only on the current observation and a compact state block. A deterministic tracker renders this state block from task progress and supplies aligned subgoal rewards, so each module can be trained with step-level SFT and refined through online RL. Across ALFWorld, WebShop, and SciWorld, our agents achieve strong performance across Qwen3-4B, Qwen3-8B and Llama-3.1-8B. With Qwen3-8B, SFT+RL reaches 89.6\% unseen success on ALFWorld, 76.8\% success on WebShop, and 66.4\% unseen success on SciWorld. They match or exceed strong published agent-training results while reducing prompt tokens per turn by 2--7$\times$ relative to controlled ReAct prompting baselines, showing that procedural context can be moved from prompts into weights.

cs.AI↗
arXiv2026

Do Phone-Use Agents Respect Your Privacy?

We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not reveal exactly what data agents type into which form entries during execution. To make this question measurable, we introduce MyPhoneBench, a verifiable evaluation framework for privacy behavior in mobile agents. We operationalize privacy-respecting phone use as permissioned access, minimal disclosure, and user-controlled memory through a minimal privacy contract, iMy, and pair it with instrumented mock apps plus rule-based auditing that make unnecessary permission requests, deceptive re-disclosure, and unnecessary form filling observable and reproducible. Across five frontier models on 10 mobile apps and 300 tasks, we find that task success, privacy-compliant task completion, and later-session use of saved preferences are distinct capabilities, and no single model dominates all three. Evaluating success and privacy jointly reshuffles the model ordering relative to either metric alone. The most persistent failure mode across models is simple data minimization: agents still fill optional personal entries that the task does not require. These results show that privacy failures arise from over-helpful execution of benign tasks, and that success-only evaluation overestimates the deployment readiness of current phone-use agents. All code, mock apps, and agent trajectories are publicly available at~ https://github.com/FreedomIntelligence/MyPhoneBench.

cs.CR↗
arXiv2026

Causally-Guided Diffusion for Stable Feature Selection

Feature selection is fundamental to robust data-centric AI, but most existing methods optimize predictive performance under a single data distribution. This often selects spurious features that fail under distribution shifts. Motivated by principles from causal invariance, we study feature selection from a stability perspective and introduce Causally-Guided Diffusion for Stable Feature Selection (CGDFS). In CGDFS, we formalized feature selection as approximate posterior inference over feature subsets, whose posterior mass favors low prediction error and low cross-environment variance. Our framework combines three key insights: First, we formulate feature selection as stability-aware posterior sampling. Here, causal invariance serves as a soft inductive bias rather than explicit causal discovery. Second, we train a diffusion model as a learned prior over plausible continuous selection masks, combined with a stability-aware likelihood that rewards invariance across environments. This diffusion prior captures structural dependencies among features and enables scalable exploration of the combinatorially large selection space. Third, we perform guided annealed Langevin sampling that combines the diffusion prior with the stability objective, which yields a tractable, uncertainty-aware posterior inference that avoids discrete optimization and produces robust feature selections. We evaluate CGDFS on open-source real-world datasets exhibiting distribution shifts. Across both classification and regression tasks, CGDFS consistently selects more stable and transferable feature subsets, which leads to improved out-of-distribution performance and greater selection robustness compared to sparsity-based, tree-based, and stability-selection baselines.

cs.LG↗
arXiv2026

Walking on Rough Terrain with Any Number of Legs

Robotics would gain by replicating the remarkable agility of arthropods in navigating complex environments. Here we consider the control of multi-legged systems which have 6 or more legs. Current multi-legged control strategies in robots include large black-box machine learning models, Central Pattern Generator (CPG) networks, and open-loop feed-forward control with stability arising from mechanics. Here we present a multi-legged control architecture for rough terrain using a segmental robot with 3 actuators for every 2 legs, which we validated in simulation for robots with 6 to 16 legs. Segments have identical state machines, and each segment also receives input from the segment in front of it. Our design bridges the gap between WalkNet-like event cascade controllers and CPG-based controllers: it tightly couples to the ground when contact is present, but produces fictive locomotion when ground contact is missing. The approach may be useful as an adaptive and computationally lightweight controller for multi-legged robots, and as a baseline capability for scaffolding the learning of machine learning controllers.

cs.RO↗
arXiv2026

BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning

Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surrogate for trust regions, we identify a critical bottleneck: fixed bounds strictly constrain the upward update margin of low-probability actions, disproportionately suppressing high-advantage tail strategies and inducing rapid entropy collapse. To address this, we introduce Band-constrained Policy Optimization (BandPO). BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions defined by f-divergences into dynamic, probability-aware clipping intervals. Theoretical analysis confirms that Band effectively resolves this exploration bottleneck. We formulate this mapping as a convex optimization problem, guaranteeing a globally optimal numerical solution while deriving closed-form solutions for specific divergences. Extensive experiments across diverse models and datasets demonstrate that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.

cs.LG↗
arXiv2026

Dataforge: Agentic Platform for Autonomous Data Engineering

The growing demand for artificial intelligence (AI) applications in materials discovery, molecular modeling, and climate science has made data preparation a critical but labor-intensive bottleneck. Raw data from diverse sources must be cleaned, normalized, and transformed to become AI-ready, where effective feature transformation and selection are essential for robust learning. We present Dataforge, an LLM-powered agentic data engineering platform for tabular data that is automatic, safe, and non-expert friendly. It autonomously performs data cleaning and iteratively optimizes feature operations under a budgeted feedback loop with automatic stopping. Across tabular benchmarks, it achieves the best overall downstream performance; ablations further confirm the roles of routing/iterative refinement and grounding in accuracy and reliability. Dataforge demonstrates a practical path toward autonomous data agents that transform raw data from data to better data.

cs.AI↗