Searcharxiv⌕ Search

arXiv subjects

Jiaxi Yang

Publications and source records attributed to Jiaxi Yang.

At least 19 recordsLinked to original sources
arXiv2026

AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?

Large Audio Language Models (LALMs) have demonstrated strong performance across a wide range of audio tasks. As they are increasingly deployed in real-world applications, ensuring their safety alignment has become more important. Although refusal mechanisms serve as a key safeguard by preventing LALMs from responding to harmful requests, they can also lead to over-refusal, where models incorrectly reject benign queries. This issue is especially challenging in the audio domain because speech that appears harmful in isolation may become benign when interpreted together with the surrounding acoustic context, such as background sounds. To study this problem, we introduce AOR-Bench (Audio Over-Refusal Benchmark), the first benchmark for over-refusal specifically designed for LALMs. AOR-Bench contains 3,000 pseudo-harmful audio samples across six scenario categories. Evaluating 12 representative LALMs from six major model families, we find that over-refusal is widespread (Figure 1) and uncover several important patterns in their safety judgments. As a preliminary effort to mitigate this issue, we further explore two lightweight strategies (e.g., Chain-of-Thought and activation steering) to reduce over-refusal.

cs.SD↗
arXiv2026

Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork

In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark ICRL4AHT, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collection, dataset construction, and online multi-episode evaluation. We evaluate representative history-conditioned ICRL algorithms, including Algorithm Distillation (AD) and Decision-Pretrained Transformer (DPT), across millions of transitions. Results reveal notable limitations: contrary to their success in single-agent domains, these baselines fail to exhibit robust test-time adaptation in multi-agent settings. Specifically, these methods frequently underperform random baselines across both unseen teammate and unseen layout tracks, with no clear in-context improvement over long horizons. These findings highlight the challenges of strategic inference under partial observability within the OvercookedV2 AHT protocol, establishing our benchmark as a critical testbed for next-generation coordination algorithms.

cs.AI↗
arXiv2026

PLOT: Enhancing Preference Learning via Optimal Transport

Preference learning in Large Language Models (LLMs) has advanced significantly, yet existing methods remain limited by modest performance gains, high computational costs, hyperparameter sensitivity, and insufficient modeling of global token-level relationships. We introduce PLOT, which enhances Preference Learning in fine-tuning-based alignment through a token-level loss derived from Optimal Transport. By formulating preference learning as an Optimal Transport Problem, PLOT aligns model outputs with human preferences while preserving the original distribution of LLMs, ensuring stability and robustness. Furthermore, PLOT leverages token embeddings to capture semantic relationships, enabling globally informed optimization. Experiments across two preference categories - Human Values and Logic & Problem Solving - spanning seven subpreferences demonstrate that PLOT consistently improves alignment performance while maintaining fluency and coherence. These results substantiate optimal transport as a principled methodology for preference learning, establishing a theoretically grounded framework that provides new insights for preference learning of LLMs.

cs.CL↗
arXiv2026

From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM

Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models.

cs.CL↗
arXiv2026

DERM-3R: A Resource-Efficient Multimodal Agents Framework for Dermatologic Diagnosis and Treatment in Real-World Clinical Settings

Dermatologic diseases impose a large and growing global burden, affecting billions and substantially reducing quality of life. While modern therapies can rapidly control acute symptoms, long-term outcomes are often limited by single-target paradigms, recurrent courses, and insufficient attention to systemic comorbidities. Traditional Chinese medicine (TCM) provides a complementary holistic approach via syndrome differentiation and individualized treatment, but practice is hindered by non-standardized knowledge, incomplete multimodal records, and poor scalability of expert reasoning. We propose DERM-3R, a resource-efficient multimodal agent framework to model TCM dermatologic diagnosis and treatment under limited data and compute. Based on real-world workflows, we reformulate decision-making into three core issues: fine-grained lesion recognition, multi-view lesion representation with specialist-level pathogenesis modeling, and holistic reasoning for syndrome differentiation and treatment planning. DERM-3R comprises three collaborative agents: DERM-Rec, DERM-Rep, and DERM-Reason, each targeting one component of this pipeline. Built on a lightweight multimodal LLM and partially fine-tuned on 103 real-world TCM psoriasis cases, DERM-3R performs strongly across dermatologic reasoning tasks. Evaluations using automatic metrics, LLM-as-a-judge, and physician assessment show that despite minimal data and parameter updates, DERM-3R matches or surpasses large general-purpose multimodal models. These results suggest structured, domain-aware multi-agent modeling can be a practical alternative to brute-force scaling for complex clinical tasks in dermatology and integrative medicine.

cs.AI↗
arXiv2026

Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

Graph diffusion models have gained significant attention in graph generation tasks, but they often inherit and amplify topology biases from sensitive attributes (e.g. gender, age, region), leading to unfair synthetic graphs. Existing fair graph generation using diffusion models is limited to specific graph-based applications with complete labels or requires simultaneous updates for graph structure and node attributes, making them unsuitable for general usage. To relax these limitations by applying the debiasing method directly on graph topology, we propose Fair Graph Diffusion Model (FairGDiff), a counterfactual-based one-step solution that mitigates topology biases while balancing fairness and utility. In detail, we construct a causal model to capture the relationship between sensitive attributes, biased link formation, and the generated graph structure. By answering the counterfactual question "Would the graph structure change if the sensitive attribute were different?", we estimate an unbiased treatment and incorporate it into the diffusion process. FairGDiff integrates counterfactual learning into both forward diffusion and backward denoising, ensuring that the generated graphs are independent of sensitive attributes while preserving structural integrity. Extensive experiments on real-world datasets demonstrate that FairGDiff achieves a superior trade-off between fairness and utility, outperforming existing fair graph generation methods while maintaining scalability.

cs.LG↗
arXiv2026

Qwen3-Coder-Next Technical Report

We present Qwen3-Coder-Next, an open-weight language model specialized for coding agents. Qwen3-Coder-Next is an 80-billion-parameter model that activates only 3 billion parameters during inference, enabling strong coding capability with efficient inference. In this work, we explore how far strong training recipes can push the capability limits of models with small parameter footprints. To achieve this, we perform agentic training through large-scale synthesis of verifiable coding tasks paired with executable environments, allowing learning directly from environment feedback via mid-training and reinforcement learning. Across agent-centric benchmarks including SWE-Bench and Terminal-Bench, Qwen3-Coder-Next achieves competitive performance relative to its active parameter count. We release both base and instruction-tuned open-weight versions to support research and real-world coding agent development.

cs.CL↗
arXiv2026

Scaling Agentic Verifier for Competitive Coding

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling. To address this limitation, we propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs that expose behavioral discrepancies among candidate solutions. Through multi-turn interaction with code execution environments, the verifier iteratively refines the candidate input generator and produces targeted counterexamples rather than blindly sampling inputs. We train the verifier to acquire this discriminative input generation capability via a scalable pipeline combining large-scale data synthesis, rejection fine-tuning, and agentic reinforcement learning. Extensive experiments across five competitive programming benchmarks demonstrate consistent improvements over strong execution-based baselines, achieving up to +10-15% absolute gains in Best@K accuracy. Further analysis reveals clear test-time scaling behavior and highlights the verifier's broader potential beyond reranking.

cs.CL↗
arXiv2026

SWE-Universe: Scale Real-World Verifiable Environments to Millions

We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic building, such as low production yield, weak verifiers, and prohibitive cost, our framework utilizes a building agent powered by an efficient custom-trained model. This agent employs iterative self-verification and in-loop hacking detection to ensure the reliable generation of high-fidelity, verifiable tasks. Using this method, we scale the number of real-world multilingual SWE environments to a million scale (807,693). We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning. Finally, we applied this technique to Qwen3-Max-Thinking and achieved a score of 75.3% on SWE-Bench Verified. Our work provides both a critical resource and a robust methodology to advance the next generation of coding agents.

cs.SE↗
arXiv2026

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models

With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all} and fail to adapt to diverse user needs and contextual constraints, leading to either under-refusal or over-refusal. In this work, we firstly explore the challenges mentioned above and develop \textbf{C}onfigurable \textbf{R}efusal in \textbf{VLM}s (\textbf{CR-VLM}), a robust and efficient approach for {\em configurable} refusal based on activation steering. CR-VLM consists of three integrated components: (1) extracting a configurable refusal vector via a teacher-forced mechanism to amplify the refusal signal; (2) introducing a gating mechanism that mitigates over-refusal by preserving acceptance for in-scope queries; and (3) designing a counterfactual vision enhancement module that aligns visual representations with refusal requirements. Comprehensive experiments across multiple datasets and various VLMs demonstrate that CR-VLM achieves effective, efficient, and robust configurable refusals, offering a scalable path toward user-adaptive safety alignment in VLMs.

cs.CV↗
arXiv2026

Evaluating and Achieving Controllable Code Completion in Code LLM

Code completion has become a central task, gaining significant attention with the rise of large language model (LLM)-based tools in software engineering. Although recent advances have greatly improved LLMs' code completion abilities, evaluation methods have not advanced equally. Most current benchmarks focus solely on functional correctness of code completions based on given context, overlooking models' ability to follow user instructions during completion-a common scenario in LLM-assisted programming. To address this limitation, we present the first instruction-guided code completion benchmark, Controllable Code Completion Benchmark (C3-Bench), comprising 2,195 carefully designed completion tasks. Through comprehensive evaluation of over 40 mainstream LLMs across C3-Bench and conventional benchmarks, we reveal substantial gaps in instruction-following capabilities between open-source and advanced proprietary models during code completion tasks. Moreover, we develop a straightforward data synthesis pipeline that leverages Qwen2.5-Coder to generate high-quality instruction-completion pairs for supervised fine-tuning (SFT). The resulting model, Qwen2.5-Coder-C3, achieves state-of-the-art performance on C3-Bench. Our findings provide valuable insights for enhancing LLMs' code completion and instruction-following capabilities, establishing new directions for future research in code LLMs. To facilitate reproducibility and foster further research in code LLMs, we open-source all code, datasets, and models.

cs.SE↗
arXiv2026

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

The dominant Fill-in-the-Middle (FIM) paradigm for code completion is constrained by its rigid inability to correct contextual errors and reliance on unaligned, insecure Base models. While Chat LLMs offer safety and Agentic workflows provide flexibility, they suffer from performance degradation and prohibitive latency, respectively. To resolve this dilemma, we propose Search-and-Replace Infilling (SRI), a framework that internalizes the agentic verification-and-editing mechanism into a unified, single-pass inference process. By structurally grounding edits via an explicit search phase, SRI harmonizes completion tasks with the instruction-following priors of Chat LLMs, extending the paradigm from static infilling to dynamic context-aware editing. We synthesize a high-quality dataset, SRI-200K, and fine-tune the SRI-Coder series. Extensive evaluations demonstrate that with minimal data (20k samples), SRI-Coder enables Chat models to surpass the completion performance of their Base counterparts. Crucially, unlike FIM-style tuning, SRI preserves general coding competencies and maintains inference latency comparable to standard FIM. We empower the entire Qwen3-Coder series with SRI, encouraging the developer community to leverage this framework for advanced auto-completion and assisted development.

cs.SE↗
arXiv2026

MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era

The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engineering and computer use requires not only efficient model computation but also sophisticated infrastructure capable of coordinating vast agent-environment interactions. However, no open-source infrastructure can effectively support large-scale training and evaluation on such complex agentic tasks. To address this challenge, we present MegaFlow, a large-scale distributed orchestration system that enables efficient scheduling, resource allocation, and fine-grained task management for agent-environment workloads. MegaFlow abstracts agent training infrastructure into three independent services (Model Service, Agent Service, and Environment Service) that interact through unified interfaces, enabling independent scaling and flexible resource allocation across diverse agent-environment configurations. In our agent training deployments, MegaFlow successfully orchestrates tens of thousands of concurrent agent tasks while maintaining high system stability and achieving efficient resource utilization. By enabling such large-scale agent training, MegaFlow addresses a critical infrastructure gap in the emerging agentic AI landscape.

cs.DC↗
arXiv2025

SWE-RM: Execution-free Feedback For Software Engineering Agents

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to provide accurate feedback, and the resulting feedback is often sparse and cannot effectively distinguish between trajectories that are both successful or both unsuccessful. In contrast, execution-free feedback from reward models can provide more fine-grained signals without depending on unit test cases. Despite this potential, execution-free feedback for realistic software engineering (SWE) agents remains underexplored. Aiming to develop versatile reward models that are effective across TTS and RL, however, we observe that two verifiers with nearly identical TTS performance can nevertheless yield very different results in RL. Intuitively, TTS primarily reflects the model's ability to select the best trajectory, but this ability does not necessarily generalize to RL. To address this limitation, we identify two additional aspects that are crucial for RL training: classification accuracy and calibration. We then conduct comprehensive controlled experiments to investigate how to train a robust reward model that performs well across these metrics. In particular, we analyze the impact of various factors such as training data scale, policy mixtures, and data source composition. Guided by these investigations, we introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference. SWE-RM substantially improves SWE agents on both TTS and RL performance. For example, it increases the accuracy of Qwen3-Coder-Flash from 51.6% to 62.0%, and Qwen3-Coder-Max from 67.0% to 74.6% on SWE-Bench Verified using TTS, achieving new state-of-the-art performance among open-source models.

cs.CL↗
arXiv2025

PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization

Recent Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation. However, their ability to create complex visualizations for scaled and structured data remains largely unevaluated and underdeveloped. To address this gap, we introduce PlotCraft, a new benchmark featuring 1k challenging visualization tasks that cover a wide range of topics, such as finance, scientific research, and sociology. The benchmark is structured around seven high-level visualization tasks and encompasses 48 distinct chart types. Crucially, it is the first to systematically evaluate both single-turn generation and multi-turn refinement across a diverse spectrum of task complexities. Our comprehensive evaluation of 23 leading LLMs on PlotCraft reveals obvious performance deficiencies in handling sophisticated visualization tasks. To bridge this performance gap, we develope SynthVis-30K, a large-scale, high-quality dataset of complex visualization code synthesized via a collaborative agent framework. Building upon this dataset, we develope PlotCraftor, a novel code generation model that achieves strong capabilities in complex data visualization with a remarkably small size. Across VisEval, PandasPlotBench, and our proposed PlotCraft, PlotCraftor shows performance comparable to that of leading proprietary approaches. Especially, on hard task, Our model achieves over 50% performance improvement. We will release the benchmark, dataset, and code at https://github.com/Speakn0w/PlotCraft-Benchmark.

cs.CL↗
arXiv2025

Turning the Tide: Repository-based Code Reflection

Code large language models (LLMs) enhance programming by understanding and generating code across languages, offering intelligent feedback, bug detection, and code updates through reflection, improving development efficiency and accessibility. While benchmarks (e.g. HumanEval/LiveCodeBench) evaluate code generation and real-world relevance, previous works ignore the scenario of modifying code in repositories. Considering challenges remaining in improving reflection capabilities and avoiding data contamination in dynamic benchmarks, we introduce LiveRepoReflection, a challenging benchmark for evaluating code understanding and generation in multi-file repository contexts, featuring 1,888 rigorously filtered test cases across $6$ programming languages to ensure diversity, correctness, and high difficulty. Further, we create RepoReflection-Instruct, a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources, used to train RepoReflectionCoder through a two-turn dialogue process involving code generation and error-driven repair. The leaderboard evaluates over 40 LLMs to reflect the model performance of repository-based code reflection.

cs.SE↗
arXiv2025

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation

Internal world models (WMs) enable agents to understand the world's state and predict transitions, serving as the basis for advanced deliberative reasoning. Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs. While the latest studies have evaluated and shown limitations in specific capabilities such as visual understanding, a systematic evaluation of VLMs' fundamental WM abilities remains absent. Drawing on comparative psychology and cognitive science, we propose a two-stage framework that assesses Perception (visual, spatial, temporal, quantitative, and motion) and Prediction (mechanistic simulation, transitive inference, compositional inference) to provide an atomic evaluation of VLMs as WMs. Guided by this framework, we introduce WM-ABench, a large-scale benchmark comprising 23 fine-grained evaluation dimensions across 6 diverse simulated environments with controlled counterfactual simulations. Through 660 experiments on 15 latest commercial and open-source VLMs, we find that these models exhibit striking limitations in basic world modeling abilities. For instance, almost all models perform at near-random accuracy when distinguishing motion trajectories. Additionally, they lack disentangled understanding -- e.g., some models tend to believe blue objects move faster than green ones. More rich results and analyses reveal significant gaps between VLMs and human-level world modeling.

cs.CL↗
arXiv2025

SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner

We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests, which inherently encapsulate high-level requirements. The core of **SWE-Flow** is the construction of a Runtime Dependency Graph (RDG), which precisely captures function interactions, enabling the generation of a structured, step-by-step *development schedule*. At each step, **SWE-Flow** produces a partial codebase, the corresponding unit tests, and the necessary code modifications, resulting in fully verifiable TDD tasks. With this approach, we generated 16,061 training instances and 2,020 test instances from real-world GitHub projects, creating the **SWE-Flow-Eval** benchmark. Our experiments show that fine-tuning open model on this dataset significantly improves performance in TDD-based coding. To facilitate further research, we release all code, datasets, models, and Docker images at [Github](https://github.com/Hambaobao/SWE-Flow).

cs.CL↗