arXiv subjects

Wei Yang

Publications and source records attributed to Wei Yang.

At least 19 recordsLinked to original sources

arXiv2026

TileCas: Cascading Kernel Development Across Programming Abstractions

Programming abstractions have traditionally been designed for humans, but code generation is increasingly performed by models and autonomous agents. We investigate abstractions for machine-driven programming through GPU and AI-accelerator kernel generation. High-level domain-specific languages (DSLs) simplify search by delegating implementation details to compilers, while lower-level representations provide finer-grained control at the cost of a larger and more complex search space. In this paper, we present TileCas, a unified, pluggable interface that enables coding agents to develop kernels across multiple editable abstraction levels. Rather than committing to a single representation, TileCas allows an agent to transfer and refine candidates across levels through Cross-Level Diagnosis, which maps correctness and performance feedback to actionable controls at different abstraction levels; Abstraction Scheduling, which selects both the candidate and representation from which subsequent refinement should proceed; and a Heterogeneous Search Tree, which preserves and revisits alternative search trajectories spanning multiple representations. We integrate TileCas with two code agents AKO and KDA, and evaluate both integrations on 50 end-to-end KernelBench Level 3 workloads across two accelerator platforms and two language models. Giving equal weight to the four accelerator-model configurations, AKO with TileCas achieves an arithmetic-mean speedup of $4.84\times$, compared with $3.75\times$ for the strongest evaluated baseline without TileCas, an improvement of 29.0%. Integrating the same interface with KDA improves its mean speedup by 69.2%, with gains in every configuration. These results show that allowing coding agents to navigate across programming abstractions can improve machine-driven software development and can be reused across different base workflows.

cs.SE↗

arXiv2026

OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Models

Video world models must preserve the visual state of the world over time, but existing evaluation protocols often rely on generated histories, video reference, or selected revisit viewpoints that can confound the assessment of a model's true memory capability. To address this, we introduce OPIS, an input-grounded benchmark that strictly anchors the assessment to a fixed set of object instances from the initial observation for evaluating multi-object memory in video world models. The OPIS dataset comprises 500 cases across real-world, embodied-robotic, and game-world domains, providing dense object-level annotations for 12,672 rigid, articulated, and deformable instances. Our object-centric evaluator combines association and explicit visibility reasoning to hierarchically measure Object (O) Presence (P), Identity (I), and Structure (S), utilizing static or dynamic evaluation tracks based on object kinematics. Across eight image-to-video or camera-conditioned world models, our proposed OPIS scores range from 48.65 to 56.01. As the reference inventory grows from less than 20 to more than 40 objects, the Presence, Identity, and Structure scores show an overall decline, with the average Identity score falling from 40.22 to 23.11. The results demonstrate that preserving the particular object instances in the input is considerably harder than generating plausible visual elements.

cs.CV↗

arXiv2026

GRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent Syllabus

Training LLM agents for policy-constrained tool environments, such as an airline backend with booking, refund, and cancellation policies, requires tasks that exercise the environment's rules individually and in combination. Existing synthesis pipelines let a model propose tasks and retain only those it immediately solves, biasing training data toward easier behaviors. We introduce Gradus (Graded Rungs of Ascending Difficulty from an Underlying System), which decouples what a task should teach from the concrete task and solution used to teach it. Without seed tasks, Gradus treats a fixed environment as a latent syllabus, extracting guarded behavioral operators that capture how actions depend on current conditions and how their effects reshape subsequent decisions. It composes these operators into increasingly demanding tasks while using corpus-level feedback to target missing outcome combinations. Crucially, Gradus jointly calibrates tasks and solutions against the environment: execution feedback identifies which side to refine while preserving the intended behavioral requirements. Verification thus becomes a recovery signal rather than a terminal filter, coupling coverage-guided exploration with the preservation of difficult examples. From off-the-shelf backbones, the resulting curriculum lifts a 30B model from 59% to 89% on $τ^2$-Bench and from 47% to 83% on CAR-Bench with an Opus 4.5 proposer, and to 76% and 62%, respectively, with an open-weight Qwen3-235B proposer. These results show the value of jointly controlling which behaviors are explored and which survive into verified training data.

cs.AI↗

arXiv2026

HRoPE: Homography Relative Positional Encoding

Geometric Relative Positional Encoding has become the primary mechanism for injecting spatial inductive biases into multi-view transformers. Existing designs condition attention on camera-level frustums or ray-marched depth, associating cross-view tokens through the sensor geometry. Such sensor-centric formulations, however, describe only where a token is observed from, leaving the rich surface geometry of the scene region depicted by the token. In this paper, we advocate a shift toward surface-aware positional encoding that explicitly grounds patch tokens in the geometry of physical surfaces. We introduce HRoPE, which represents the local geometry of each patch as a slanted 3D plane, following the slanted support-window assumption of classical multi-view stereo. We inject token-level, plane-induced homographies into attention as relative transformations. This equips the transformer with a geometric prior for rectifying perspective distortions and aligning patch features across viewpoints. Our encoding requires no ground-truth geometry: the plane parameters can be predicted end-to-end under a view-synthesis objective alone, or derived from foundation models. Extensive experiments on RealEstate10K, CO3Dv2, and DL3DV show that our best variant of HRoPE consistently outperforms the evaluated geometric positional encodings for novel view synthesis. Extensive ablations and analysis show the effectiveness of the proposed encoding. Please refer to our project page at: https://gaohchen.github.io/HRoPE

cs.CV↗

arXiv2026

Beyond Confidence: Rethinking Uncertainty Calibration in Deep Code Models

Deep learning models have shown significant promise in code-related tasks. While confidence calibration techniques have been proposed to improve model reliability, their effectiveness in real-world tasks with strict accuracy requirements remains uncertain. In this paper, we investigate two key questions: first, whether existing measurement metrics, including confidence scores and uncertainty metrics, are effective for guiding selective prediction; and second, whether existing calibration techniques can improve these metrics to better identify cases where model predictions are likely to succeed or fail. We conduct a systematic study on defect prediction and vulnerability detection using seven code models, evaluating thirteen uncertainty signals and three widely used post-hoc calibration methods. Our analysis reveals three major findings: (1) even strong uncertainty signals can remain poorly calibrated and provide limited separation at the high-confidence end, constraining selective prediction in practice; (2) standard post-hoc calibrators often improve calibration scores but do not consistently translate into better selective prediction behavior; and (3) commonly used calibration metrics can disagree with selective prediction performance, underscoring the need to evaluate both jointly. Moreover, our findings motivate a decision-oriented view of reliability in deep code models, where calibrated scores must be evaluated together with selective-prediction quality and retained-region risk before they can support accept--defer deployment.

cs.SE↗

arXiv2026

From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents

Long-term memory enables LLM agents to reuse past experiences, yet retrieving relevant memories does not necessarily provide sufficient evidence for answering a query. Essential information may remain fragmented across memory records, obscured by abstraction, or disconnected from the relations required for reasoning. We identify this relevance-sufficiency gap and propose QEMem, a framework that reformulates memory utilization as the construction of query-specific evidence sets, shifting the focus from individual retrieval relevance to collective evidential support. QEMem integrates three complementary mechanisms: query-guided discovery retrieves evidence across multiple memory granularities; source-grounded reification organizes it into structured ViewCards with explicit evidential roles and source references; and sufficiency-guided refinement selectively recovers missing information. Operating on existing memory stores without modifying memory formation, QEMem achieves 91.43% LLM-judge accuracy on LoCoMo with Claude Opus 4.5, outperforming the strongest evaluated baseline, MemR$^3$, by 7.6 percentage points and NEMORI by 10.7 points under a shared memory store. Further analyses demonstrate improved evidence coverage and strong performance on questions requiring cross-session evidence integration.

cs.AI↗

arXiv2026

Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation

Social network simulation aims to model collective opinion dynamics in large populations, but existing LLM-based simulators mainly focus on aggregate dynamics while largely ignoring individual internal states. This limits their ability to capture opinion reversals driven by gradual individual shifts and makes them unreliable in long-horizon simulations. We propose MF-MDP, a social simulation framework that tightly couples macro-level collective dynamics with micro-level individual states. MF-MDP explicitly models per-agent latent opinion states with a state transition mechanism, combining individual Markov Decision Processes at the micro level with a mean-field collective framework at the macro level. This allows individual behaviors to change internal states gradually rather than trigger instant reactions, enabling the simulator to distinguish agents that are close to switching from those that are far from switching, capture opinion reversals, and maintain accuracy over long horizons. Across real-world events, MF-MDP supports stable simulation of long-horizon social processes with up to 40,000 interactions, compared with about 300 in the baseline MF-LLM, while reducing long-horizon KL divergence by 75.3% (1.2490 to 0.3089) and reversal KL by 66.9% (1.6425 to 0.5434), significantly mitigating the drift observed in MF-LLM. Code is available at ai4ss.github.io/M2Sim.

cs.SI↗

arXiv2026

Terrarium: Growing Personal Assistants via Scalable Synthesis of App Worlds

Advances in large language models (LLMs) have brought the vision of a general-purpose personal assistant closer to reality. Such assistants could provide a unified natural-language interface to a broad ecosystem of applications. However, real-world applications do not readily support training at scale because access is often restricted and their state is difficult to reset. To address this challenge, we introduce Terrarium, a framework that synthesizes executable App Worlds from real-world application information, generates training task packages with evaluator-side rubrics from these worlds, and iteratively validates and refines both through agent rollouts. For App World synthesis, Terrarium organizes public Web information and in-application observations into structured app specifications that guide the construction of self-contained runtimes with callable operations and mutable, resettable state. For task synthesis, Terrarium constructs tasks grounded in App World state together with evaluator-side outcome rubrics that assess success without prescribing reference trajectories. We construct a training suite of 275 App Worlds and 13,344 tasks for outcome-based reinforcement learning across three Qwen3 model scales (4B, 8B, and 14B parameters). Across these scales, models trained with Terrarium outperform the corresponding Qwen3 models by an average of 18.34 percentage points on the $τ^2$-bench and 10.94 percentage points on the AppWorld bench. These results suggest that app-grounded world and task synthesis offers a scalable path toward general-purpose assistants capable of operating across broad application ecosystems.

cs.LG↗

arXiv2026

Skill-Adaptive Imitation Learning for UI Test Reuse

To alleviate the substantial cost of manually crafting user interface (UI) test cases, UI test migration aims to automatically generate test cases for a target mobile application (app) by adapting those from a source app that shares similar functionalities. Traditionally, this process has been approached as a sequential UI-event-mapping problem, where events in the source app are mapped to those in the target one based on their textual descriptions. Prior research has extensively focused on enhancing the event-mapping accuracy of NLP models. Although the advent of large language models (LLMs) with impressive NLP capabilities suggests the potential for near-perfect event-mapping, our study demonstrates that even the highly accurate event-mapping of LLMs is insufficient to address the implementation discrepancies between the source and the target apps, reducing the overall effectiveness of LLM-driven solutions for UI test migration. To address this challenge, in this paper, we propose SAIL, a skill-adaptive imitation learning framework designed to enhance the effectiveness of UI test migration through two key designs. First, SAIL leverages the source test cases as demonstrations and employs a multi-level abstraction of test cases' underlying skills, so as to extract the testing information from source test cases as the knowledge base for the subsequent test generation on the target app. Second, SAIL selectively reuses a subset of the learned skills to guide the generation of test cases for the target app with its novel context- and history-aware skill adaptation. While SAIL can be instantiated with any imitation learning techniques, we utilize the in-context learning capabilities of LLMs to instantiate SAIL. Evaluations results show that SAIL substantially improves the effectiveness of UI test migration, with 149\% higher success rate than state-of-the-art approaches.

cs.SE↗

arXiv2026

Characterizing Overconfident Failure in LLM-Based Code Generation

Large language models (LLMs) are increasingly used for automated code generation, but generated programs can appear syntactically plausible while still failing execution-based correctness checks. Existing validation methods, such as testing and program analysis, remain essential but are often incomplete, costly, or applied only after generation. Model-derived uncertainty is therefore a natural early reliability signal. This paper studies the dilemma of overconfidence in code LLMs where incorrect programs are often generated with token-level confidence comparable to correct programs. We study this dilemma across four open-source code models and three execution-based benchmarks. Our analysis begins by investigating whether existing uncertainty metrics provide reliable proxies for execution correctness in code generation. We then characterize overconfidence at both global and local token levels, asking whether incorrect programs remain indistinguishable from correct ones under confidence and entropy summaries, including selective generation and the limits of instruction tuning. Finally, we evaluate whether common mitigation strategies reduce this failure mode. Our study yields four findings. First, existing uncertainty signals provide only partial and model-dependent evidence of execution failure. Second, overconfidence persists at both program and token levels, and uncertainty-based selection does not consistently improve accepted-set accuracy. Third, instruction tuning can increase certainty on failing generations without consistently improving correctness discrimination. Fourth, common mitigation techniques improve specific aspects of reliability but do not reliably resolve overconfident failure. Our exploratory latent analysis suggests that hidden representations may encode correctness-related signals that output confidence does not expose.

cs.SE↗

arXiv2026

SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning

Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision. Realizing this promise requires not only updating the agent, but also evolving its training experience as its capabilities change. However, most existing pipelines rely on static datasets or separately updated synthesis models, causing previously useful tasks to become trivial while overly difficult tasks remain uninformative. This growing mismatch between agent capability and training experience limits sustained self-improvement. To address this problem, we propose SynCo, an agentic data synthesis co-training framework for self-evolving LLMs based on multi-agent reinforcement learning. SynCo jointly optimizes two independently parameterized agents: a Synthesizer that constructs training tasks from the Reasoner's evolving capability state, and a Reasoner that learns from the resulting experience. Each synthesized task induces multiple Reasoner rollouts whose outcomes provide complementary rewards to both agents. Correctness feedback improves the Reasoner, while task quality, answer reliability, and outcome-grounded teachability guide the Synthesizer. Their updates are fed back into subsequent synthesis rounds, allowing the task-solving policy and its training distribution to evolve together. Extensive experiments across eight mathematical reasoning benchmarks demonstrate that SynCo substantially outperforms a broad range of existing synthetic-data methods and controlled baselines, achieving the strongest overall performance while deriving most of its gains from previously unsolved problems.

cs.AI↗

arXiv2026

Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning

The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning value for the current task agent. Existing methods increasingly incorporate environment feedback, data validation, or learner failures, but still face a feedback-to-decision gap: observed weaknesses do not directly specify how future synthesis should change, or whether they can be represented by the current synthesis space. To address this gap, we propose EvoSyn, a learning-feedback-driven multi-agent framework that organizes synthesis around a revisable state specifying what interaction factors can be deliberately generated and where synthesis effort should be allocated. A role-specialized multi-agent system translates learner feedback into synthesis revisions, while a Designer allocates synthesis directions and a Planner grounds them into executable experience. This process enables within-space adaptation toward weak or under-covered regions and synthesis-space expansion that promotes newly discovered factors into explicit generation controls. Experiments on $τ^2$-Bench and CAR-Bench show that EvoSyn improves average task success by 13.3 points over the strongest synthesis baseline, while producing higher-quality and structurally broader synthetic experience and discovering controllable factors missed without learner feedback.

cs.AI↗

arXiv2026

From Priors to Projections: Geometry and simplified MIMO demodulation of probabilistic shaping

Probabilistic shaping (PS) is a well-known method to achieve improved performance upon a regular quadrature amplitude modulation (QAM) by taking the target constellation and making the distribution of underlying points non-uniform. It has been extensively studied over the years for the additive white Gaussian noise (AWGN) and Rayleigh fading channels. However, the potential of probabilistic shaping in the multiple-input and multiple-output (MIMO) setting needs further investigations. In this paper, we prove that if shaped symbols follow Maxwell-Boltzmann distribution, the optimal maximum a posteriori (MAP) detection is equivalent to the case of uniform constellation with a simple preprocessing step. Our approach has multiple benefits. It enables to utilize the same processing chain for both shaped and unshaped system, which simplifies the receiver architecture. This technique can be applied for both linear MMSE and nonlinear (near-)MAP demapper types. In addition, the complexity of adaptive methods such as sphere decoding can be reduced.

cs.IT↗

arXiv2026

MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation

Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token costs, or continuous flow models that depend on heuristic connectivity decoders. Next-scale generation paradigms offer a compelling alternative by enabling parallel intra-scale token prediction and coarse-to-fine refinement from global structure to local topology; yet, existing methods derive hierarchical scales via progressive mesh simplification and invert them sequentially. This eliminates intra-scale parallelism and scales generation steps linearly with face count. In this paper, we propose MeshOctave, which instead defines scale through dyadic spatial grid resolutions, framing coarsening as a deterministic collapse that merges vertices sharing a voxel cell and inherits connectivity. Its inverse operation, split-and-rewire, determines which octant sub-vertices are instantiated for each coarse face and resolves local connectivity using discrete structural tokens. These per-face operations require no serialization, each scale transition is modeled as an unordered set that adds one bit of coordinate precision, naturally supporting dynamic-length meshes and adaptive resolution refinement. We construct a scale-conditioned masked-uniform discrete diffusion model to learn split-and-rewire operation from resolution collapse hierarchies. MeshOctave outperforms strong baselines in geometric fidelity and topological validity by a non-trivial margin, while supporting adaptive resolution refinement and extending naturally to mesh subdivision tasks.

cs.CV↗

arXiv2026

Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems

Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect effective communication, a favorable agent architecture, or simply additional reasoning? Because communication methods are commonly evaluated within the systems they were designed for, these factors are difficult to disentangle. Final accuracy further merges corrected errors and corrupted answers into a single outcome, obscuring how communication changes decisions. We introduce Independent--Communicate--Revise (ICR), a controlled framework that evaluates communication as answer revision following independent reasoning. ICR fixes initial reasoning trajectories, measures correction and preservation conditional on both agents' initial correctness, and uses a no-message revision control to quantify gains beyond additional reasoning. Across four reasoning benchmarks, our audit of textual and latent communication reveals that similar aggregate accuracy can conceal substantially different revision behaviors. Compared with transmitting answers alone, full reasoning increases correction while reducing preservation on all four benchmarks, so richer messages amplify beneficial and harmful influence alike. Receiver-policy comparisons on MedQA and GPQA-D further show that a structured verification policy shifts every channel toward greater preservation and lower correction, while its effect on selectivity varies across channels and tasks. These findings challenge treating communication quality as an intrinsic property of a channel. ICR therefore recenters evaluation on selective revision, providing a unified framework for examining how message content and receiver policies jointly produce benefits and harms.

cs.AI↗

arXiv2026

Names without information: Attention allocation and rent transfer in a zero-fundamental token market

Asset names are associated with investor trading and asset prices, but where names and issuer quality are formed jointly, information, preference and attention-coordination explanations are difficult to distinguish. We study a token launchpad on which tokens issued under the default template use the same contract code, have a fixed supply and carry no cash flows, while names can be registered at almost no cost, cannot be verified and may be reused. Using all 458,174 default-template tokens launched from February to June 2026 and a sample split by creator entity fixed in advance, we find that the share of tokens attracting an outside buyer rises from 34.9% to 52.8% across name-appeal deciles, but within creator and creation minute the effect of appeal is small and does not replicate in the validation sample. Conditional on early capital inflow and creator fixed effects, the residual effects of names on migration, peak market capitalization and post-peak drawdown are statistically equivalent to zero, and buyers who follow appealing names earn no economically meaningful premium. The same name attracts less capital with each reuse, names whose first token draws more capital are copied sooner, and competition over names mainly transfers wealth among buyers.

cs.CE↗

arXiv2026

One QK Channel, Many Sources: Tracing Low-Precision Attention Collapse

A bfloat16 transformer can train normally, then collapse abruptly. Prior work links collapse to structured attention errors and shows QK normalization disrupts their compounding. Distinct low-precision errors trigger the same collapse, leaving unclear whether each needs a fix at its source or one shared route can be blocked instead. We isolated the fault behind a reproduced GPT-2-class collapse to the streaming-softmax accumulator, where an fp32 streaming core repairs it, and turned it into an assay for moving a controlled error across sources. Using it, we found that errors placed outside attention still drove the same QK spectral runaway, and that correcting only QK kept training stable while the fault stayed active. This is a source-channel dissociation: fault source is not failure channel. It held across tested architectures and scales, and reproduced on a second GPU architecture. As a causal probe, projecting each update off the current QK weights' leading three singular directions held the query projection's largest singular value to 11.1, whereas removing equal energy elsewhere left it at 237: the QK channel causally drives the early runaway. What lets the injected error in is temporal sign-coherence, its per-head sign persisting across steps, not aggregate deviation; once inside, the runaway shows as attention-logit saturation. QK-Guard, a dormant controller, tests this by switching on parameter-free QK normalization at the first monitored threshold crossing. On the runs designated for this test, the QK-local action prevented the failure of each matched or same-configuration unguarded run; on plain GPT-2, all 12 final train and validation losses were within 0.03 nat of same-configuration always-on QK-norm, and both methods ran 60k steps without collapse. Intervention at the QK locus therefore suffices in place of a fix at each source.

cs.LG↗

arXiv2026

A Three-Layer Framework for Measuring Names and Its Census Application on a Token Launchpad

Asset names influence market behavior, yet standardized name measurement remains lacking. Existing processing fluency measures focus mainly on alphabetic languages and are unsuitable for Chinese names. Cultural meanings usually require manual coding, limiting large-scale analysis, while name competition through reuse and semantic crowding remains underexplored. This study constructs a dataset of 513,647 naming attempts from the Four token launchpad on BNB Chain between February and June 2026 and proposes a three-layer framework for name measurement. The form layer measures linguistic fluency using 38 Chinese-oriented features. The reference layer captures cultural meanings through human coding and large language model expansion with reliability evaluation. The relation layer measures name reuse, semantic crowding, and lexical variation. The three layers are largely independent, with correlations below 0.11. Census analysis reveals that name diversity follows Heaps' law, new-name adoption declines over time, name reuse shows heavy-tailed patterns, and repeated naming occurs at distinct creator-level and cross-creator time scales. Cultural events also trigger rapid naming responses. The framework, annotated dataset, and code are released to support scalable analysis of naming behavior in digital markets and other naming environments.

cs.CE↗