Search arXiv⌕ Search

arXiv subjects

Han Li

Publications and source records attributed to Han Li.

At least 19 recordsLinked to original sources
arXiv2026

MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation

Recommender systems (RecSys) are increasingly emphasizing scaling, leveraging larger architectures and more interaction data to improve personalization. Yet, despite the optimizer's pivotal role in training, modern RecSys pipelines almost universally default to Adam/AdamW, with limited scrutiny of whether these choices are truly optimal for recommendation. In this work, we revisit optimizer design for scalable recommendation and introduce MuonRec, the first framework that brings the recently proposed Muon optimizer to RecSys training. Muon performs orthogonalized momentum updates for 2D weight matrices via Newton-Schulz iteration, promoting diverse update directions and improving optimization efficiency. We develop an open-source training recipe for recommendation models and evaluate it across both traditional sequential recommenders and modern generative recommenders. Extensive experiments demonstrate that MuonRec reduces converged training steps by an average of 32.4\% while simultaneously improving final ranking quality. Specifically, MuonRec yields consistent relative gains in NDCG@10, averaging 12.6\% across all settings, with particularly pronounced improvements in generative recommendation models. These results consistently outperform strong Adam/AdamW baselines, positioning Muon as a promising new optimizer standard for RecSys training. Our code is available.

cs.IR↗
arXiv2026

Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning

Detailed image captioning is usually framed as an amount problem: a model should mention more visual facts while avoiding hallucination. However, autoregressive VLMs generate captions as ordered sequences, and later generations may be produced under weaker or noisier visual grounding. We therefore argue that long-form captioning should be studied not only by what facts are mentioned, but also by where they appear. We introduce a position-aware rubric representation that decomposes dense human references into atomic visual claims, verifies generated captions against those claims, and induces a quartile-wise composition of supported, hallucinated, and generic content. This lens reveals two qualitatively different failures in long captions: models tend to produce unsupported specificity in the middle, while the final portion often escapes into vague, non-evidential language rather than simply accumulating more hallucination. A same-reference human control does not exhibit these patterns; additional human audits examine the visual validity of the induced labels. Motivated by this diagnosis, we propose PAGER (Position-Aware Grounded Evidence Reinforcement), a GRPO training objective with separate signals for supported fine-grained middle evidence, evidence-bearing tail continuation, claim coverage, and content-aware length control. The result is a closed loop: the same ordered claim representation identifies where long captions fail and supplies the position-specific reward needed to repair those failures. Experiments on detailed-caption benchmarks show that PAGER improves position-wise grounding and pairwise caption preference while preserving competitive global caption quality.

cs.CV↗
arXiv2026

A Formal Diagnostic Framework for Graph Repair Systems

Graph-based data representations excel at capturing relations among entities, e.g., for semantic web, artificial intelligence, or database applications, and their utility depends critically on their quality, usually enforced via graph schemas. These schemas are often violated, e.g., during data ingestion, calling for repair actions to achieve compliance. This paper presents a formal diagnostic framework for graph repair methods. Current methods often lack rigor and generality, since they rely on ad hoc test datasets. Our method starts, instead, from a compliant graph and uses an abstract rewriting system to systematically introduce schema violations while ensuring provable coverage of the constraints in the schema. We apply the framework to several repair methods, including those based on large language models, and assess their performance across multiple metrics. Results show that our framework effectively differentiates the performance of different methods across various constraints, highlighting the importance of fine-grained, systematic tools for graph repair.

cs.DB↗
arXiv2026

VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation

Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a rule-consistent game or narration synchronized to on-screen events. A different route is emerging: multimodal agents that write code to render every frame and synthesize every sound. We introduce VibeVideoBench, a benchmark for evaluating agents on code-driven video generation. Its 239 self-contained tasks in English and Chinese span 12 categories, from data stories and music-driven pieces to classroom lessons and paper explainers; each asks an agent, running in its native harness inside a sandbox with no image or video generation model, to deliver a finished MP4 with sound within one hour. Evaluation is hierarchical and evidence-based: program checks of the delivery spec, about 13k task-specific rubric checks traced to the requirements they enforce, and five quality dimensions anchored per task, scored by three VLM judge panels. Across nine frontier agent systems and 2,151 scored rollouts, GPT-6 Astra and Claude Opus 5.5 rank first and second with both the judges and human annotators, and the strongest system satisfies every core requirement on 76.3% of tasks. Delivery is a second axis: counting missing videos as zero changes the ranking, and three quarters of the lost videos are final renders that started too late, ran too slowly or never started, a failure of how agents plan their hour. Agents build their own rendering pipelines and inspect their own frames, yet how much they look does not predict quality. The judges' ranking of the systems closely matches blind human preferences.

cs.CV↗
arXiv2026

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain constrained to isolated scenarios, narrow action spaces, or synthetic data, failing to capture the holistic nature of authentic human behavior. To bridge this gap, we introduce OmniBehavior, the first predictive user simulation benchmark constructed entirely from real-world data, integrating long-horizon, cross-scenario, and heterogeneous behavioral patterns into a unified framework. Based on this benchmark, we first provide empirical evidence that previous datasets with isolated scenarios suffer from tunnel vision, whereas real-world decision-making relies on long-term, cross-scenario causal chains. Extensive evaluations of state-of-the-art LLMs reveal that current models struggle to accurately predict these complex behaviors, with performance plateauing even as context windows expand. Crucially, a systematic comparison between simulated and authentic behaviors uncovers a fundamental structural bias: LLMs tend to converge towards a positive average person, exhibiting hyper-activity, persona homogenization, and a utopian bias. This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.

cs.CL↗
arXiv2026

OmniSimulator: Aligning Small Language Models for Authentic Heterogeneous Behavior Modeling

Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-quality data can substantially improve model reasoning and downstream task performance. However, the upper bound of user simulation is still constrained by the model's reasoning paradigm: native chain-of-thought often degenerates into shallow pattern matching and fails to adequately model the behavioral factors underlying real user decisions. In this paper, we propose OmniSimulator, a novel training framework designed to improve the predictive ability of small LLMs for realistic user simulation on short-video platform environments. Specifically, OmniSimulator organizes behavior-oriented reasoning through a structured schema with five dimensions, carefully selects data from real user-behavior scenarios, and introduces a teacher model to generate high-quality reasoning traces under the proposed schema, helping small models learn behavior-relevant reasoning patterns rather than relying on superficial behavioral correlations. Based on this process, we construct 9,881 high-quality training instances from three months of historical interaction trajectories of 200 real users, averaging about 50 distilled examples per user. Experimental results show that OmniSimulator improves the average score of Qwen3-8B by 34.33%, achieves performance competitive with Claude-Sonnet-4.5, and supports smaller-scale, self-hosted deployment. These results suggest that learning structured behavior-oriented reasoning patterns is a promising direction towards scalable and high-fidelity LLM-based user simulation.

cs.CL↗
arXiv2026

Pointwise decay of steady Navier--Stokes flows with Navier-slip boundary condition in two-dimensional channels

We establish a pointwise decay estimate for steady incompressible Navier--Stokes flows in two-dimensional channels with positive Navier friction coefficient. Specifically, for the arbitrary-flux solutions constructed by Sha, Wang, and Xie \cite{SWX22f}, under suitable outlet conditions and weighted geometric bounds on the channel walls, we show \[ |\Bu(x_1,x_2)|\le \frac{C}{f(x_1)}, \] where $f$ is the channel width. Our decay rate is optimal in the cross-sectional supremum norm when the prescribed flux is nonzero. The main difficulty is that rescaling by the local width changes the Navier friction coefficient into a potentially large parameter. The key technique is to establish a local Stokes boundary estimate uniform in this parameter.

math.AP↗
arXiv2026

GSM: Efficient Language Modeling with Shared Global State

Improving language model efficiency requires not only cheaper operations but also eliminating redundant computation. We argue that effective modeling requires information accessibility and computational depth, but not repeated historical retrieval across layers. Guided by this principle, we introduce the Global State Model (GSM), a causal encoder--decoder architecture that separates historical information acquisition from deep computation. The encoder progressively aggregates long-range information through multi-stage sparse retrieval into a fixed-size shared state, while decoder layers perform successive transformations over this state without repeated historical access. This design makes decoder attention and cache costs independent of history length, while dependency-aware pruning further reduces prefill computation. Experiments across multiple model scales show that GSM achieves downstream performance comparable to matched DeepSeek-V4.1-Flash-based baselines, with improvements at some scales, while preserving long-context retrieval capabilities. GSM also improves training and inference throughput and reduces cache overhead. These results demonstrate that eliminating architectural redundancy offers an effective path toward efficient language modeling without sacrificing information accessibility or computational depth.

cs.CL↗
arXiv2026

SWE-at-Scale: Scalable Issue Synthesis from Historical Bug Fixes

As coding agents become increasingly capable, robust evaluation requires a broader and more diverse supply of verifiable software engineering (SWE) tasks. However, real-world tasks are constrained by the natural frequency of issue reporting and the substantial cost of manual curation. Furthermore, existing synthetic approaches rely primarily on the pretrained knowledge of large models coupled with heuristic prompting, often failing to capture the authentic, complex mechanics of software failures. To exponentially scale SWE task production, we introduce SWE-at-Scale, a framework that automatically synthesizes realistic issues by reverse-engineering real-world software fixes. Our key insight is that historical fixes encapsulate deep mechanistic knowledge of bug formation: inverting a fix transforms repair supervision into bug-induction supervision grounded in actual development scenarios. SWE-at-Scale transfers these learned bug patterns to novel code contexts, repeatedly sampling diverse bug typologies to construct executable SWE tasks. Extensive experiments show that SWE-at-Scale generates more diverse and realistic SWE tasks than current synthesis baselines while posing greater challenges to state-of-the-art coding agents. Notably, SWE-at-Scale can generate distinct bug types from a single code context, with bug diversity scaling robustly even up to 200 generations per file. Overall, SWE-at-Scale turns finite real-world fixes into reusable supervision for scalable synthesis of realistic, diverse, and challenging SWE tasks.

cs.SE↗
arXiv2026

Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of use, which a successful task attempt can leave untested. We introduce Socratic Skill Learning (SSL), which interleaves expert teaching with Student practice. An Educator guides investigation while the Student remains the sole environment operator and Skill author, able to question, test, and adapt advice. To test reuse beyond the learning task, we construct SkillTransferBench, with 35 task families and 408 executable cases, pairing public variation specifications with held-out evaluation in fresh solver sessions. On the main 22-family, 155-case cohort, Fixed-Window SSL reaches 0.801 utility, versus 0.723 without a Skill, 0.761 for adapted Trace2Skill (trajectory distillation), and 0.751 for adapted SKILL-KD (contrastive distillation). Across three model pairs on shared families, interleaved guidance outperforms expert authoring and post-hoc teaching. Process analysis links guidance to Student writing and package revision; a case study shows the Student testing and refining a proposed procedure for later reuse. As demand for new lessons falls, the cost of fixed-window review grows. Issue-Guided SSL tracks unresolved questions across Skill revisions to select and focus review, reaching 0.805 utility with 61.7% fewer Educator tokens and 16.9% fewer total acquisition tokens than Fixed-Window SSL on the main cohort.

cs.AI↗
arXiv2026

SWEPatchTest: Evaluating Software Tests Beyond Reproduction

Coding agents use generated tests to decide whether a proposed patch satisfies an issue's requirements. A suite that fails on the buggy program and passes after applying the reference patch can still accept an incorrect patch or reject a correct patch. We introduce SWEPATCHTEST, a test-generation benchmark with 619 tasks from SWE-bench Pro, SWE-bench Multilingual, and DeepSWE and 82,579 candidate patches collected from coding-agent trajectories. By replaying each suite on the buggy and patched codebases, \benchmark jointly measures issue reproduction, acceptance of correct patches, and rejection of incorrect patches. Joint Validation Rate (JVR), which requires all three criteria on the same task, exposes failures hidden by single-reference evaluation: the best-performing configuration achieves only 9.21% JVR despite reproducing the reference transition on 59.29% of tasks. We further use validation scores to select and scale demonstrations for supervised fine-tuning (SFT). The resulting training recipe approximately triples JVR and improves downstream repair across three SWE-bench benchmarks. Patch discrimination thus provides both a diagnostic measure of test quality and an execution-based signal for curating agent training data.

cs.SE↗
arXiv2026

PathPilot: An Adaptive Question-Conditioned Multi-Magnification Navigation Agent for Whole-Slide Image Analysis

The diagnostic capability of WSI agents relies on effective slide navigation to identify diagnostically relevant regions and efficiently integrate evidence across the slide. While in clinical practice, pathologists dynamically examine slides across multiple scales, integrating global and cellular evidence in a sequential manner, existing AI navigation approaches mostly operate at a single fixed magnification or rely on predefined magnification traversal. This mismatch prevents existing methods from modeling cross-magnification interactions and adaptive magnification selection inherent to real diagnostic workflows. We propose PathPilot, a clinically consistent multi-magnification WSI navigation agent that explicitly models cross-magnification localization and evidence-adaptive exploration. Specifically, we introduce a CrossMagLoc that learns magnification-specific diagnostic localization from pathologist viewing behavior and integrates information from adjacent magnifications to identify the diagnostically most relevant region within the current ROI, thereby providing a diagnostically informed starting point for subsequent question-conditioned exploration. We further introduce an EviRegionSearch that starts question-conditioned exploration from this region, progressively accumulating question-relevant evidence and adaptively determining the next navigation action according to the remaining evidence requirement. Their iterative interaction enables PathPilot to sequentially explore across ROIs and magnifications until sufficient evidence is acquired. Extensive QA evaluations across five cohorts demonstrate consistent superiority over competing SOTA methods on inter/external cohorts, respectively, validating question-conditioned evidence acquisition across regions and magnifications that mirrors the sequential, knowledge-driven navigation of pathologists.

cs.CV↗
arXiv2026

EnactOpt: Diagnosis-Guided Harness Evolution for Embodied Agents

Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into subsequent decisions. Failures can arise not only from limited model capabilities, but also from how the harness presents evidence and guides its use. These model-external mechanisms provide an adaptation target without updating model parameters, but task-specific interaction experience can be costly to collect. Task-level outcomes alone do not reveal whether relevant evidence was missing from the model input or was available but inadequately used. Moreover, these two aspects are coupled: effective action guidance may require evidence that the current context omits, while exposing that evidence alone does not ensure an appropriate response. We introduce EnactOpt, which uses limited execution feedback to jointly evolve reusable textual skills and context-construction code while keeping the underlying models and runtime fixed. It diagnoses adjacent decisions by relating action feedback to the actual model input and subsequent action. Structured episode summaries guide joint revisions through prompt-level edit operators, and candidate harnesses undergo compatibility checks and validation-based retention. Across VLABench, ALFWorld, and Embodied Agent Interface (EAI), EnactOpt improves task success by approximately 10-27 percentage points over the initial harnesses and outperforms the evaluated GEPA, TextGrad, and Trace2Skill baselines. These gains extend to task conditions not used for harness evolution or candidate selection. The results support a complementary route to embodied adaptation: turning limited execution experience into reusable behavioral improvements by jointly refining how evidence is presented and acted upon.

cs.RO↗
arXiv2026

UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence

Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framework exploring a third path: semantic-group shared interest memory. By utilizing Semantic IDs (SIDs) and a dual-level attention strategy, UxSID captures target-aware preferences without the heavy cost of item-specific models. This end-to-end architecture balances computational parsimony with semantic awareness, achieving state-of-the-art performance and a 0.337% revenue lift in large-scale advertising A/B test.

cs.AI↗
arXiv2026

EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems

In large-scale enterprise settings, centralized multi-agent systems (MAS) are increasingly adopted, in which a coordinator delegates user requests to lightweight, domain-specialized sub-agents. While this architecture improves modularity, scalability, and cost efficiency, its reliability depends not only on accurate routing but also on sub-agents' ability to calibrate their responses to capability constraints. In particular, sub-agents built on smaller fine-tuned models often struggle with such calibration, leading them to over-answer ambiguous, underspecified, misrouted, or unsupported requests and produce hallucinated outputs instead of actionable feedback. To address this challenge, we present EARS (Explanatory Abstention for Reliable Sub-Agent Modeling), a production-oriented framework that reframes sub-agent abstention as an inter-agent communication protocol: a sub-agent does not merely abstain, but exposes an actionable failure state to the coordinator. EARS curates human-agent interaction data using an ensemble of calibrated LLM-as-a-Judge models, producing structured abstention labels and rationales under a taxonomy of sub-agent failure modes. These data are used to fine-tune sub-agents to detect failure conditions and return rationales for coordinator-level clarification, rerouting, or fallback. We evaluate EARS in a large-scale production e-commerce assistant supporting enterprise business intelligence workflows. EARS improves the overall response pass rate from 68.5% to 78.9%, demonstrating that sub-agent-side explanatory abstention improves MAS reliability.

cs.MA↗
arXiv2026

TestPrism: Rethinking Test Evaluation Beyond a Single Reference

Large language model (LLM) coding agents have advanced test generation across diverse programming tasks. However, the common practice of evaluating tests against a single reference solution overlooks alternative valid implementations and can overstate test quality. We introduce TestPrism, comprising 300 test tasks from 17 sources and 3000 candidate implementations, evenly split between valid and invalid solutions. Its primary metric, Joint Success Function, requires the generated tests to fail on the initial program state, accept every valid candidate, and reject every invalid candidate. Across fourteen baseline coding agent configurations, Joint Success Function reaches only 28.00%, whereas single reference success reaches 59.67%. Our analysis reveals missed behaviors, unsupported assertions, and faulty test construction. To address these weaknesses, we introduce TestHelix, which combines heterogeneous synthesis of test and repair pairs with peer cross validation and recursive self improvement (RSI). Across two models, TestHelix improves Joint Success Function by 8.67 to 9.00 percentage points over the native harness comparators in the TestHelix evaluation

cs.SE↗
arXiv2026

When Sub-Agents Work in Parallel: The Promises and Pitfalls of Dynamic Concurrency in Long-Horizon Coding Tasks

As coding agents advance from bounded software engineering tasks toward long horizon development, dynamic concurrency offers a promising way to scale complex development tasks. Under this policy, agents decide during execution whether and how to spawn concurrent sub-agents. Model capability largely determines outcomes on shorter tasks, whereas long horizon development makes orchestration central to task completion. Existing work, focused on coding agent failures on shorter tasks or collaboration in predefined multiagent workflows, offers little insight into dynamic concurrency in frontier agents across task complexity. We study dynamic concurrency as an execution policy through controlled comparisons of matched Codex, Claude Code, and Kimi Code executions with the policy enabled or disabled. Across 354 tasks and 2,124 executions spanning a range of task complexities and execution horizons, we evaluate its end to end effects and scheduling behavior, and analyze matched trajectories to characterize 13 concurrency specific failure modes, 28 observable patterns, and the conditions under which it provides an advantage.

cs.SE↗
arXiv2026

AMBER: Training Long-Horizon Web Agents through Append-Only Memory

Modern language-model agents increasingly interact with external environments over long-horizon, multi-step trajectories, where the accumulated interaction history can quickly exceed practical context budgets. To ensure reliability, agents must maintain factual information over long horizons, remember execution errors and corrective feedback, and track progress across actions. Several approaches have been proposed to achieve this without the need for maintaining the entire execution history in context, such as using the reasoning and action history, learning to maintain a fixed-size memory through an overwrite mechanism, and periodic summarization. Although overwrite memory can in principle retain anything an append-only memory can, it must learn to carry each fact through every subsequent rewrite, which is difficult to learn from sparse outcome rewards; for interactive applications like web agents, we find that trained overwrite memories delete key information required by the trajectory, as well as corrective feedback received from the environment. We introduce AMBER (Append-only Memory Bank for Evidence Retention) - a simple and scalable framework where an agent jointly learns to reason, act, and write free-form memory, while an append-only rule guarantees retention by construction. This allows AMBER to be trained end-to-end with reinforcement learning from outcome rewards without the need for extensive curated SFT data. On WebArena Lite, AMBER improves average success over overwrite-based memory by 4.09 percentage points, increases the fraction of tasks solved in five repeated runs by 4.8 percentage points, and matches an overwrite baseline trained on substantially more expensive curated supervision. AMBER achieves these improvements while maintaining a practical token budget, providing a strong balance between context efficiency, task performance, and reliable long-horizon execution.

cs.AI↗