Searcharxiv⌕ Search

arXiv subjects

Shen Yan

Publications and source records attributed to Shen Yan.

At least 19 recordsLinked to original sources
arXiv2026

xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems

Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally make in practice. Real-world requests are often open-ended, casually specified, and context-dependent, requiring models not only to follow explicit instructions but also to infer unstated needs from user background and situational context. We introduce xDailyBench, a benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities. The tasks are grounded in requests that users have actually completed or genuinely intended to accomplish with AI, and are evaluated with fine-grained binary rubrics covering both explicit and implicit requirements. We evaluate 11 frontier models under standardized agentic settings. The best models achieve a task-level score of 75.6\%, while all models perform substantially worse on implicit than explicit requirements, with gaps no less than 9 percentage points. These results reveal implicit requirement inference as a persistent bottleneck for reliably satisfying real-world everyday user needs.

cs.AI↗
arXiv2026

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating architectural advantage with extra FLOPs. We study looping on Mixture-of-Experts Transformers while closely matching per-token FLOPs, total non-embedding parameters, and KV cache. Through a series of ablations, we arrive at a recipe we call SMELT (Sparse MoE Transformer, middle layers Loop Twice), which loops the middle half of layers twice while matching the unlooped Baseline on all three budgets. We scale SMELT across four sizes up to 54B non-embedding parameters and fit a separate Chinchilla-style scaling law for each architecture. SMELT's loss drops faster with compute, saving 6.8--18.0\% of training FLOPs on the compute-optimal frontier. The advantage transfers to downstream benchmarks beyond what validation loss predicts, is largest on Code, and grows with sample length and the number of in-context examples. Mechanistic analysis shows that the second visit reduces the attention sink and redirects mass toward content-relevant tokens, an inductive bias that may underlie the observed performance gains. These results show that looping can improve Transformers even under budget matching, offering a practical recipe that turns depth reuse into measurable gains.

cs.LG↗
arXiv2026

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Changing this harness while holding model weights fixed can substantially alter task performance. Current agent evaluations typically report downstream performance under a chosen harness, leaving a model's ability to develop the harness itself comparatively underexplored. We introduce HarnessDev, a benchmark that shifts the unit of evaluation from task outputs to runnable infrastructure. HarnessDev covers two stages. In Creation, the agent starts from a minimal seed and a small number of cases, then builds a complete execution system. In Evolution, it starts from its own created harness and iteratively revises it using downstream execution feedback, with the goal of improving benchmark performance. We then evaluate each constructed harness on capability (task success on held-out benchmarks) and efficiency (execution-token cost). The reported Creation results cover six creator LLMs, four domains, and five downstream benchmarks totaling 2,207 unique downstream instances, with hidden evaluation tasks withheld from development. We find that generated harnesses remain substantially behind mature human-engineered references on code and on search and research, while matching or exceeding the selected references on writing and machine-learning experimentation, with large variation in execution cost. Evolution produces some performance gains, but they are unstable and transfer only partially to held-out tasks. Experiments with a fixed runtime model further show that the gains depend strongly on the model executing the harness, indicating limited transfer across models.

cs.SE↗
arXiv2026

REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation

As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token prediction supervises what follows a context but leaves the intermediate reasoning behind that continuation implicit. We introduce \textbf{REER-PT}, a scalable framework that extends Reverse-Engineered Reasoning (REER) to raw pre-training data. REER-PT identifies continuations that are difficult to predict but can still be inferred from the preceding context, and inserts concise reasoning annotations that reconstruct the missing connection between context and continuation. Candidate annotations are generated and refined offline, with perplexity serving as the optimization signal. Constraints on length and target leakage filter out unhelpful or trivial annotations. This sparse transformation preserves the source text and remains compatible with standard next-token prediction, avoiding online reasoning rollouts during pre-training. We apply REER-PT to transform a source pre-training corpus into an augmented one. Across augmented-data, original-token, and selected-continuation comparisons, perplexity reductions range from 0.42 to 7.29, and only about 0.05\% of annotation 13-grams appear verbatim in the source text. We then train two 680M-parameter models with the same architecture and training configuration on the source and augmented corpora, respectively. The augmented-data model gains up to 2.07 percentage points on several knowledge and reasoning benchmarks. Together, the perplexity analysis indicates improved continuation predictability, while the controlled pre-training experiments suggest that this augmentation can improve model performance without changing the standard pre-training objective.

cs.CL↗
arXiv2026

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them as fixed policies. It therefore remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions. We introduce \textbf{S\textsuperscript{3}Gym}, an interactive benchmark for evaluating LLM self-improvement through three coupled capabilities: \textbf{Self-Testing}, \textbf{Self-Judging}, and \textbf{Self-Improvement}. S$^3$Gym separates permissive exploration from strict held-out evaluation and instantiates this protocol in seven text-based games with executable environment verifiers. We evaluate three pathways for incorporating interaction experience: direct History ICL, score-conditioned Summary Memory, and parameter Training. Our experiments reveal that self-improvement is neither automatic nor uniform. Context-level experience improves performance for several model--game pairs, but the most effective pathway depends strongly on the task structure: summaries are beneficial when experience can be compressed into reusable strategic rules, yet often underperform raw history when success depends on precise, state-contingent information. Parameter training produces substantial gains on some tasks, but also exhibits unstable improvement and severe negative transfer on others. These findings show that recognizing successful actions is insufficient; agents must also transform feedback into executable and transferable policies. S$^3$Gym provides a unified framework for diagnosing this process and identifying the bottlenecks that prevent agents from translating interaction experience into reliable self-improvement.

cs.CL↗
arXiv2026

Aspire: Can Models Self-Evolve from Vague Goals?

Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capability goal while downstream evaluation tasks remain hidden. The agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-Agent reference. Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements.

cs.CL↗
arXiv2026

Repo2Skill-Evo: Repository Skills Go Stale in Silence

Large language model (LLM) agents increasingly operate over evolving software repositories, where success depends on repository-specific procedural knowledge: which APIs to call, which scripts to run, and which conventions the current release expects. Agent skills externalize this knowledge into reusable units, and prior work shows that they can improve agent performance. What remains unclear is whether that improvement is durable. The same version specificity that makes a skill useful also makes it fragile: after a release, it may become stale without raising any explicit signal, while continuing to provide obsolete guidance. Externalizing knowledge into a skill can therefore make its decay invisible. We study whether agents can keep this externalized knowledge current. Repo2Skill-Evo casts each release transition as a skill-maintenance task: given a V1 skill set and the official V1-to-V2 patch, an agent must update obsolete skill content while preserving guidance that remains valid. Across 57 real-world repositories and 105 selected release transitions, every evaluated transition invalidates part of the V1 skill set. Yet six frontier agents reach only 29.9%-69.7% avg@3 macro F1 under a patch-grounded removal metric that balances stale-content recall against over-editing precision. Across runs, two opposing errors dominate: incomplete coverage of affected files in the skill set leaves stale content untouched, while overbroad editing is associated with higher recall but lower precision. Repository skills go stale in silence, and even frontier agents cannot reliably maintain them.

cs.AI↗
arXiv2026

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30\% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks.

cs.AI↗
arXiv2026

Chain-of-Experience for Continual LLM Improvement

Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to as Chain-of-Experience (CoE), where models accumulate experiential traces through iterative interactions with self or environmental feedback to form a continual improvement loop beyond zero-shot inference. We instantiate CoE with diverse feedback mechanisms, including model self-feedback and environmental signals such as correctness or public coding test pass rates, and evaluate across math, coding, and knowledge domains using 8 LLMs, including GPT-5, Gemini-2.5 Pro, Claude-4.5 Sonnet. Our study shows that leveraging iterative experience consistently outperforms feedback-free baselines, achieving substantial gains with self feedback alone, alongside a 5.6% overall improvement and 19% lower API cost across tasks and models. We further show that combining complementary feedback channels (e.g., model and correctness signals) yields additional gains, and that CoE delivers higher accuracy per token than existing test-time strategies. We observe a positive correlation between LLM base ability and improvement capacity, and show that models remain robust under weak or spurious feedback, with different feedback contributing to distinct improvement aspects and most gains emerging early in the iterations.

cs.CL↗
arXiv2026

Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents

When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in the user turn, while coding-agent benchmarks emphasize final task success. We introduce Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts, placed on the five configurable surfaces a deployed agent reads. To separate compliance from coincidence we introduce Against-Prior Accuracy (AP-Acc), which scores only rules labeled as opposing unprompted defaults, observed by re-running tasks with the rule withheld across nine probe builds and curated otherwise. Across 12 frontier models, accuracy spans 72.1-85.9% and AP-Acc 66.1-78.6%; every model is worse on against-prior rules, by 3.6 to 7.4 points (mean 5.81), and the direction survives a common-support analysis with item-clustered intervals. Aggregate scores therefore overstate compliance by a model-specific margin: prior control leaves the top build unchanged and exchanges three adjacent rank pairs. A counterbalanced conflict pilot on nine separate builds adds a second result: pooled precedence does not follow prompt depth, with system prompts, project files, and user instructions ahead of tool and skill descriptions.

cs.AI↗
arXiv2026

PiLoT v2: Pixel-to-Orthogonal Map Alignment for Free-view UAV Geo-localization

Real-time, drift-free UAV geo-localization is essential for autonomous missions in GNSS-denied environments. The pioneering system, PiLoT, achieves high precision via Neural Pixel-to-3D Registration, aligning UAV video streams with a single rendered reference view from 3D meshes. However, its reliance on heavy 3D meshes incurs massive storage overheads, complex map acquisition, and significant computational rendering costs, severely hindering deployment on embedded platforms. To address these bottlenecks, we propose PiLoT v2, a lightweight yet robust evolution that shifts the paradigm to direct pixel-to-orthogonal map registration for free-view UAV geo-localization. By leveraging True Digital Orthophoto Maps (TDOMs) and Digital Surface Models (DSMs) as the reference substrate, PiLoT v2 replaces GPU-intensive 3D rendering with a highly efficient, CPU-friendly map cropping operation. To bridge the severe geometric discrepancy between these 2.5D orthogonal crops and free-view oblique UAV imagery, we train a cross-view feature registration network using a novel, large-scale geometrically annotated dataset. Furthermore, we integrate onboard sensor prior--specifically gravity direction and single-point laser rang--directly into the pose optimization manifold to enhance robustness against cross-view visual degradation. Experimental results demonstrate that PiLoT v2 achieves performance comparable to, or even exceeding, its Pixel-to-3D predecessor, while offering drastically lower storage and computational costs.

cs.CV↗
arXiv2026

On the Residual Scaling of Looped Transformers: Stability and Transferability

Looped (weight-tied) Transformers apply a shared residual block $N$ times ($h \leftarrow h + \varepsilon\,f(h)$, same $f$ at each step), increasing effective depth without adding parameters. Prior depth-scaling analyses prescribe $\varepsilon = 1/\!\sqrt{L}$ for depth-$L$ residual networks. We show that this is insufficient for looped architectures: weight sharing makes residual updates correlated across iterations, requiring the stronger scaling $\varepsilon = 1/N$. For multi-layer blocks ($L$ unique layers looped $N$ times), we derive a factored parameterization $\varepsilon = \lambda/(N\!\sqrt{L})$ that separates the two sources of growth: $1/N$ controls the within-layer loop correlation, and $1/\!\sqrt{L}$ controls the across-layer variance. A key consequence is that the optimal learning rate depends only on the number of unique layers $L$, not on the loop count $N$, enabling direct hyperparameter transfer from small to large $N$ without retuning. Experiments on looped Transformers confirm that $1/N$ scaling improves trainability and yields better loss than $1/\!\sqrt{N}$ scaling across loop counts.

cs.LG↗
arXiv2026

Dynamic Linear Attention

The scalability of Large Language Models (LLMs) to long contexts is fundamentally constrained by the quadratic complexity of standard attention, motivating the adoption of linear attention mechanisms with sub-quadratic cost. To improve representation capacity under long contexts, recent approaches organize memory in a multi-state manner. However, existing multi-state linear attention methods rely on fixed state merging policies that cannot adapt to dynamically varying token importance, irreversibly obscuring critical tokens and causing severe error accumulation over long sequences. To address this limitation, we propose DLA, a dynamic memory modeling framework for multi-state linear attention. DLA introduces (i) Information-Aware Dynamic State Merging, which adaptively determines state boundaries based on token-level information variation, preserving high-resolution representations around semantic transitions while aggressively summarizing stable regions, and (ii) Capacity-Bounded Memory Modeling, which maintains a fixed-size, chronologically ordered state cache by selectively merging adjacent low-information states to control memory growth with minimal information loss. We pre-train DLA on two different linear attention models and evaluate on 16 datasets across three categories. Experimental results demonstrate the superiority of DLA over state-of-the-art.

cs.CL↗
arXiv2026

Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields

Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents can operate graphical user interfaces to complete long-horizon, high-value professional workflows across diverse domains. Current GUI benchmarks still predominantly focus on general-purpose software, relatively simple applications, and short-horizon tasks, leaving it largely unknown whether modern agents can follow user instructions to autonomously operate domain-specific professional software and accomplish economically valuable work in an end-to-end manner. To bridge this gap, we introduce Workflow-GYM, a benchmark for long-horizon GUI tasks centered on professional domains and specialized software environments. Through extensive experiments on state-of-the-art models, we find that even the strongest models achieve only slightly above 30% success rates, highlighting that professional long-horizon GUI workflows remain highly challenging for current GUI agents. Further analysis reveals that current agents struggle to maintain long-horizon workflow consistency, frequently exhibiting workflow stage omission, error propagation, objective drift, and insufficient understanding of professional software environments. Our findings provide important insights into the limitations of current agent systems and suggest key directions for the next generation of GUI-agent research.

cs.AI↗
arXiv2026

Knowledge Index of Noah's Ark

Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotation that permits lazy consensus; and unaudited ranking instability under bounded test budgets. We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines, with two formal results. First, we cast representativeness as a coverage-style objective over expert-elicited anchors and operationalize disciplinary representativeness through a proxy, yielding a (1-1/e) greedy approximation (Proposition 1); the guarantee applies to the proxy, not to population representativeness. Second, we prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality, with incentive-compatibility threshold B > Delta C / Delta p_min (Theorem 1). Evaluating 42 models from 13 labs, the top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%, leaving substantial headroom below saturation. The full leaderboard shows a tiered structure rather than a smooth total order: a small frontier tier lies above 48%, a dense strong-model tier spans roughly 38-45%, and low-performing models remain only modestly above the 10% chance baseline. Tool augmentation adds up to 5.17 points across the five tool-use evaluations, with gains varying substantially across models. We report bootstrap ranking-stability statistics to make bounded-budget variance explicit and to discourage over-interpretation of adjacent ranks.

cs.AI↗
arXiv2026

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insufficiently explored, particularly for designing and balancing long-context data mixtures. In this work, we present a systematic study of long-context continued pre-training for LVLMs, extending a 7B model from 32K to 128K context with extensive ablations on long-document data. We first show that long-document VQA is substantially more effective than OCR transcription. Building on this observation, our ablations further yield three key findings: i) for sequence-length distribution, balanced data outperforms target-length-focused data (e.g., 128K), suggesting that long-context ability requires generalizable key-information retrieval across various lengths and positions; ii) retrieval remains the primary bottleneck, favoring retrieval-heavy mixtures with modest reasoning data for task diversity; and iii) pure long-document VQA largely preserves short-context capabilities, suggesting that instruction-formatted long data reduces the need for short-data mixing. Based on these findings, we introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget. MMProLong improves long-document VQA scores by 7.1% and maintains strong performance at 256K and 512K contexts beyond its 128K training window, without additional training. It further generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision. Overall, our study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models.

cs.CV↗
arXiv2026

MegaScale-Omni: A Hyper-Scale, Workload-Resilient System for MultiModal LLM Training in Production

As the foundational component of versatile AI applications, training an multimodal large language model (MLLM) relies on multimodal datasets with dynamic modality mixture proportions and sample length distributions. However, existing MLLM systems remain inefficient under dynamic workloads, due to statically coupled decisions of resource allocation and model parallelization between encoders and the LLM backbone. This paper presents MegaScale-Omni, an industrial-grade MLLM training system tailored for dynamic workload adaption and hyper-scale deployment. MegaScale-Omni is built upon the training scheme of encoder-LLM multiplexing with three key innovations: (1) Decoupled parallelism strategies with long-short sequence parallelism for encoders to process variable-length samples, and full-fledged 5D parallelism for the LLM backbone, both organized under a communication-efficient parallelization layout. (2) Unified encoder-LLM representations for flexible, extensible colocation, and a new paradigm of encoder-LLM joint pipeline with workload resilience. (3) Workload balancing techniques via decentralized grouped reordering in data loaders and adaptive resharding from encoder to LLM ranks. MegaScale-Omni is deployed as the foundation of our in-house large-scale MLLM training tasks with thousands of GPUs. Our experimental results demonstrate $1.27\times$-$7.57\times$ throughput improvement under production-grade dynamic workloads, as compared to four state-of-the-art systems.

cs.DC↗
arXiv2026

AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision

Despite the rapid progress in data-driven 3D vision, aerial geometric 3D vision remains a formidable challenge due to the severe scarcity of large-scale, high-fidelity training data. Existing benchmarks, predominantly biased toward ground-level or object-centric views, do not account for complex viewpoint transformations and diverse environmental conditions in UAV-based sensing. To bridge this critical gap, we propose AirZoo, a unified large-scale dataset and benchmark for grounding aerial geometric 3D vision. AirZoo possesses three appealing properties: 1) Scalable Generation Pipeline: Leveraging freely available, world-scale photogrammetric 3D meshes, it renders vast outdoor environments with customizable UAV flight trajectories and configurable weather/illumination. 2) Comprehensive Scene Diversity: It provides the most extensive coverage of region types to date (spanning 378 regions across 22 countries), systematically encompassing both highly structured urban landscapes and complex unstructured natural environments. 3) Rich Geometric Annotations: Each frame provides synchronized, pixel-level metric depth and precise 6-DoF geo-referenced poses, essential for geometry-aware learning. Through three rigorous evaluation tracks -- aerial image retrieval, cross-view matching, and multi-view 3D reconstruction -- we demonstrate that AirZoo serves as a powerful pre-training engine. Extensive experiments on both public and newly collected real-world benchmarks reveal that fine-tuning on AirZoo yields substantial performance gains for SoTA models (e.g., MegaLoc, RoMa, VGGT, and Depth Anything 3), establishing a new performance upper bound for aerial spatial intelligence.

cs.CV↗