Existing hard-label text attacks often rely on inefficient "outside-in" strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient "inside-out" framework. It employs a Multi-Armed Bandit algorithm to identify Pivot Sets—combinatorial token groups acting as prediction anchors—and strategically perturbs them to induce label flips. This approach captures inter-word dependencies and minimizes query costs. Extensive experiments across traditional models and Large Language Models demonstrate that PivotAttack consistently outperforms state-of-the-art baselines in both Attack Success Rate and query efficiency.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
100,903篇论文
第 677 / 5046 页
Algorithm Visualization (AV) helps students build mental models by animating algorithm execution states. Recent LLM-based systems such as CODE2VIDEO generate AV videos in an end-to-end manner. However, this paradigm requires the system to simultaneously simulate algorithm flow and satisfy video rendering constraints (element layout, color schemes, etc.), a complex task that induces LLM hallucinations. This results in reduced execution success rates, element overlap, and inter-frame inconsistencies.To address these challenges, we propose ALGOGEN, a novel paradigm that decouples algorithm execution from rendering. We first introduce Visualization Trace Algebra (VTA), a monoid over algorithm visual states and operations. The LLM then generates a Python tracker that simulates algorithm flow and outputs VTA-JSON traces, a JSON encoding of VTA. For rendering, we define a Rendering Style Language (RSL) to templatize algorithm layouts. A deterministic renderer then compiles algorithm traces with RSL into Manim, LaTeX/TikZ, or Three.js outputs[Manim, TikZ, and Three.js are respectively a Python animation engine, a LaTeX vector graphics package, and a JavaScript 3D rendering library.].Evaluated on a LeetCode AV benchmark of 200 tasks, ALGOGEN achieves an average success rate improvement of 17.3% compared to end-to-end methods (99.8% vs. 82.5%). These results demonstrate that our decoupling paradigm effectively mitigates LLM hallucinations in complex AV tasks, providing a more reliable solution for automated generation of high-quality algorithm visualizations. Demo videos and code are available at: .
Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and avoid drifting into incorrect facts as the interaction grows longer. Existing approaches primarily focus on extending the context window, introducing external memory, or applying context compression, yet these methods still face limitations such as contextual inertia and state drift. To address these challenges, we propose the Adaptive Context Refactoring (ACR) Framework, which dynamically monitors and reshapes the interaction history to mitigate contextual inertia and state drift actively. ACR is built on a library of context refactoring operators and a teacher-guided self-evolving training paradigm that learns when to intervene and how to refactor, thereby decoupling context management from the reasoning process. Extensive experiments on multi-turn dialogue demonstrate that our method significantly outperforms existing baselines while reducing token consumption. Our code is available at https://github.com/ClannadKno/multi-turn.
Identifying conditions that a certain drug takes therapeutic effect on a target disease is crucial for clinical decision-making support. However, most existing biomedical information extraction methods have focused on identifying only relations between drugs and diseases, while largely overlooking the context-specific conditions where such relations can apply. To address this problem, we introduce the task of applicability condition extraction for therapeutic drug–disease relations from biomedical research literature. We create the first dataset that has manually annotated triples of drugs, diseases, and applicability conditions on biomedical paper abstracts with 1,119 drug-disease pairs. Using this dataset, we systematically evaluate the performance of a range of existing methods. In addition, we propose a new method that enhances LoRA to consider relations between drugs and diseases. Our method consistently outperforms strong baselines across different evaluation settings.
Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying. While semantic transcription is well-studied, the precise localization of non-verbal events remains a critical yet under-explored challenge. Current methods suffer from insufficient task definitions with limited category coverage and ambiguous temporal granularity. They also lack standardized evaluation frameworks, hindering the development of downstream applications. To bridge this gap, we first develop a refined taxonomy of 21 vocal events, with a new categorization into discrete (standalone) versus continuous (mixed with speech) types. Based on the refined taxonomy, we introduce WESR-Bench, an expert-annotated evaluation set (900+ utterances) with a novel position-aware protocol that disentangles ASR errors from event detection, enabling precise localization measurement for both discrete and continuous events. We also build a strong baseline by constructing a 1,700+ hour corpus, and train specialized models, surpassing both open-source audio-language models and commercial APIs while preserving ASR quality. We anticipate that WESR will serve as a foundational resource for future research in modeling rich, real-world auditory scenes.
The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has shifted from simple context extension to the development of dedicated agentic memory systems. However, existing approaches typically rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms. These design choices create a persistent mismatch between stored information and task-specific reasoning demands, while leading to the unchecked accumulation of logical inconsistencies over time. To address these challenges, we propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities. AMA employs a hierarchical memory design that dynamically aligns retrieval granularity with task complexity. Specifically, the Constructor and Retriever jointly enable multi-granularity memory construction and adaptive query routing. The Judge verifies the relevance and consistency of retrieved content, triggering iterative retrieval when evidence is insufficient or invoking the Refresher upon detecting logical conflicts. The Refresher then enforces memory consistency by performing targeted updates or removing outdated entries. Extensive experiments on challenging long-context benchmarks show that AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods, demonstrating its effectiveness in maintaining retrieval precision and long-term memory consistency.
The emergence of groundbreaking large language models capable of performing complex reasoning tasks holds significant promise for addressing various scientific challenges, including those arising in complex clinical scenarios. To enable their safe and effective deployment in real-world healthcare settings, it is urgently necessary to benchmark the diagnostic capabilities of current models systematically. Given the limitations of existing medical benchmarks in evaluating advanced diagnostic reasoning, we present DiagnosisArena, a comprehensive and challenging benchmark designed to rigorously assess professional-level diagnostic competence. DiagnosisArena consists of 1,113 pairs of segmented patient cases and corresponding diagnoses, spanning 28 medical specialties, deriving from clinical case reports published in 10 top-tier medical journals. The benchmark is developed through a meticulous construction pipeline, involving multiple rounds of screening and review by both AI systems and human experts, with thorough checks conducted to prevent data leakage. Our study reveals that even the most advanced reasoning models, o3-mini, o1, and DeepSeek-R1, achieve only 45.82%, 31.09%, and 17.79% accuracy, respectively. This finding highlights a significant generalization bottleneck in current large language models when faced with clinical diagnostic reasoning challenges. Through DiagnosisArena, we aim to drive further advancements in AI’s diagnostic reasoning capabilities, enabling more effective solutions for real-world clinical diagnostic challenges. We openly share the benchmark and evaluation tools for further research and development.
While Large Language Models (LLMs) demonstrate remarkable reasoning, complex optimization tasks remain challenging, requiring domain knowledge and robust implementation. However, existing benchmarks focus narrowly on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation. To address this, we introduce OptiVerse, a comprehensive benchmark of 1,000 curated problems spanning neglected domains, including Stochastic Optimization, Dynamic Optimization, Game Optimization, and Optimal Control, across three difficulty levels: Easy, Medium, and Hard. The experiments with 22 LLMs of different sizes reveal sharp performance degradation on hard problems, where even advanced models like GPT-5.2 and Gemini-3 struggle to exceed 27% accuracy. Through error analysis, we identify that modeling logic errors remain the primary bottleneck. Consequently, we propose a Dual-View Auditor Agent that improves the accuracy of the LLM modeling process without introducing significant time overhead. OptiVerse will serve as a foundational platform for advancing LLMs in solving complex optimization challenges.
Large Language Models (LLMs) achieve strong results on code generation, but single model inference remains brittle on tasks that require iterative refinement. Existing multi agent frameworks improve reliability, yet they often incur substantial token and latency overhead. We introduce PairCoder, a framework that brings pair programming to autonomous LLM collaboration. PairCoder assigns one model to code generation and the other to review, and switches roles when repeated errors suggest that the current interaction has stalled. Across 13 LLMs on HumanEval, PairCoder consistently improves over single model inference. On eight representative backbones, it reaches 91.0% pass@1 and improves over single model inference by up to 20.3% while reducing token usage by 40% to 70% relative to multi agent baselines. Many heterogeneous pairings also outperform both constituent models, suggesting that the framework generalizes across model families. These results position PairCoder as an effective and deployment conscious alternative to heavier multi agent systems.Code is available at https://github.com/yisuanwang/PairCoder
Beyond Surface-Level Pattern Trap: LLM Agents for Faster and Smarter Cross-Architecture Code Migration
PDF ↗The problem of surface-level pattern mapping represents a critical yet underexplored failure mode in large language model (LLM) reasoning, and is particularly acute in cross-architecture code migration of high-performance libraries. On low-resource, low-level code, insufficient coverage in pretraining data often leads LLMs to rely on superficial name- or type-based correspondences, rather than principled refactorization and reasoning grounded in core functional semantics and architecture-specific optimization intents. This tendency severely hampers the effectiveness of LLMs in complex migration scenarios.To address these challenges, we propose FSCM, a multi-agent framework for cross-architecture migration. FSCM decouples complex implementation details through functional mining and code refactoring, guiding LLMs to focus on invariant semantic anchors across architectures. By mitigating surface-level pattern traps, FSCM improves both functional correctness and performance when targeting emerging architectures. Extensive experiments on the challenging real-world OpenCV library migration tasks demonstrate substantial improvements over state-of-the-art baselines, achieving up to 22% higher correctness rates over Copilot and 43.04x speedup on RISC-V platforms. Code and data are available at: https://anonymous.4open.science/r/code-F8D4.
Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages
PDF ↗We present a phoneme-level analysis of automatic speech recognition (ASR) for two low-resourced and phonologically complex East Caucasian languages, Archi and Rutul, based on curated and standardized speech–transcript resources totaling approximately 50 minutes and 1 hour 20 minutes of audio, respectively. Existing recordings and transcriptions are consolidated and processed into a form suitable for ASR training and evaluation. We evaluate several state-of-the-art audio and audio–language models, including wav2vec2, Whisper, and Qwen2-Audio. For wav2vec2, we introduce a language-specific phoneme vocabulary with heuristic output-layer initialization, which yields consistent improvements and achieves performance comparable to or exceeding Whisper in these extremely low-resource settings. Beyond standard word and character error rates, we conduct a detailed phoneme-level error analysis. We find that phoneme recognition accuracy strongly correlates with training frequency, exhibiting a characteristic sigmoid-shaped learning curve. For Archi, this relationship partially breaks for Whisper, pointing to model-specific generalization effects beyond what is predicted by training frequency. Overall, our results indicate that many errors attributed to phonological complexity are better explained by data scarcity. These findings demonstrate the value of phoneme-level evaluation for understanding ASR behavior in low-resource, typologically complex languages.
AI-generated content has evolved from monolithic models to modular workflows, particularly on platforms like ComfyUI, enabling customization in creative pipelines. However, crafting effective workflows requires great expertise to orchestrate numerous specialized components, presenting a steep learning curve for users. To address this challenge, we introduce ComfyUI-R1, the first large reasoning model for automated workflow generation. Starting with our curated knowledge bases, we construct long chain-of-thought (CoT) reasoning data, including node selection, workflow planning, and code-level workflow representation. ComfyUI-R1 is trained through a two-stage framework: (1) CoT fine-tuning for cold start, adapting models to the ComfyUI domain; (2) reinforcement learning for incentivizing reasoning capability, guided by a fine-grained rule-metric hybrid reward, ensuring format validity, structural integrity, and node-level fidelity. Experiments show that our 7B-parameter model achieves a 97% format validity rate, along with high pass rate, node-level and graph-level F1 scores, surpassing prior state-of-the-art methods that employ leading closed-source models such as GPT-4o and Claude series. Qualitative analysis further highlights our model’s strength in synthesizing intricate workflows with diverse nodes, aligning with human instructions, and generalizing to newly introduced nodes, underscoring the potential of long CoT reasoning in AI art creation.
Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined. We test whether broadcast community discussion improves stand-up comedy writing in a controlled multi-agent sandbox: in the discussion condition, critic and audience threads are recorded, filtered, stored as social memory, and later retrieved to condition subsequent generations, whereas the baseline omits discussion. Across 50 rounds (250 paired monologues) judged by five expert annotators using A/B preference and a 15-item rubric, discussion wins 75.6% of instances and improves Craft/Clarity (Δ = 0.440) and Social Response (Δ = 0.422), with occasional increases in aggressive humor.
Self-play preference optimization has emerged as a prominent paradigm for aligning large language models (LLMs). It typically involves a language model to generate on-policy responses for prompts and a reward model (RM) to guide the selection of chosen and rejected responses, which can be further trained with direct preference optimization (DPO). However, the role of prompts remains underexplored, despite being a core component in this pipeline. In this work, we investigate how prompts of varying difficulty influence self-play preference optimization. We use the mean reward of sampled responses of a prompt as a proxy for its difficulty. We first find that difficult prompts exhibit substantially inferior self-play optimization performance compared to easy prompts for language models. Moreover, incorporating difficult prompts into training fails to enhance overall performance and, in fact, leads to slight degradation compared to training on easy prompts alone. Third, there is a clear upward trend in optimization performance as prompt difficulty decreases. We also observe that the performance gap between difficult and easy prompts tends to close as the model capacity increases, suggesting that prompt difficulty interacts with the model capacity. Building on these findings, we explore strategies to mitigate the adversary effect of difficult prompts on final performance. We demonstrate that only training on a small portion (30%) of the easiest prompts improves overall self-play performance on AlpacaEval 2 and Arena-Hard. We also report failed attempts and lessons learned.
Code localization is a primary bottleneck in automated software development. While parallel tool execution can accelerate discovery, existing agents suffer from a 34.9% redundant tool invocation rate, negating the benefits of parallelism. We introduce FuseSearch, which reframes parallel code localization as a quality–efficiency co-optimization problem. By defining tool efficiency—the ratio of novel information gain to total invocations—we employ a two-stage SFT and RL pipeline to train models in adaptive parallel strategies. Unlike fixed-breadth methods, FuseSearch dynamically adjusts search breadth based on task context, transitioning from exploration to refinement. On SWE-bench Verified, FuseSearch-4B matches SOTA performance (84.7% file-level and 56.4% function-level F_1 scores) while being 93.6% faster, using 67.7% fewer turns and 68.9% fewer tokens. Our findings demonstrate that efficiency-aware training inherently boosts quality by eliminating noisy, redundant signals, enabling high-performance, low-cost localization agents. Code: https://github.com/sxthunder/FuseSearch
Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings
PDF ↗Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate algorithmic hiring systems. We study prompt injection in automated résumé screening, defined as subtle self-promotional text that introduces no new qualifications but is designed to influence LLM evaluations. Using controlled experiments, we show that prompt injection reliably improves applicant rankings when résumé quality is homogeneous and few candidates inject. However, its effectiveness rapidly diminishes as more candidates inject, collapsing when manipulation becomes widespread. When candidate quality is heterogeneous, prompt injection is less effective on average, but can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns. Overall, LLM-based screening is most vulnerable when manipulation is rare and candidate quality differences are small.
Culturally aware safeguards are crucial for AI alignment in real-world settings, where safety extends beyond common sense and encompasses diverse local values, norms, and region-specific regulations. However, building large-scale, culturally grounded datasets is challenging due to limited resources and a scarcity of native annotators. Consequently, many safeguard models rely on machine translation of English datasets, often missing regional and cultural nuances. We present a novel agentic data-generation framework to scalably create authentic, region-specific safety datasets for Southeast Asia (SEA). On this foundation, we introduce the SEA-Guard family, the first multilingual safeguard models grounded in SEA cultural contexts. Evaluated across multiple benchmarks and cultural variants, SEA-Guard consistently outperforms existing safeguards at detecting regionally sensitive or harmful content while maintaining strong general safety performance.
Large language models (LLMs) have shown promising advancements in tackling human-level tasks, wherein generating workflows for collaborative AI systems remains a critical and challenging step. To explore this frontier, we introduce ComfyFlow, a comprehensive benchmark to evaluate current LLMs’ ability to generate executable and instruction-following AIGC workflows in ComfyUI. The dataset includes 400 diverse visual generation tasks across 20 categories, supported by 10K training examples constructed from knowledge bases, which contain detailed annotations for 2,480 nodes and 3,298 workflows. We establish a systematic evaluation protocol that quantifies performance across multiple dimensions, ranging from basic format validity to multi-level hallucination rates. Our extensive evaluations show that: 1) ComfyFlow presents a substantial challenge even for top-tier proprietary LLMs such as GPT-5.1 and the Claude series; 2) Open-source models achieve new state-of-the-art results after post-training, yet struggle with long-horizon planning as the number of nodes increases; 3) Different post-training strategies offer complementary benefits in following instructions and mitigating hallucinations. By establishing both a challenging benchmark and a principled evaluation scheme, ComfyFlow lays the foundation for developing more intelligent and reliable collaborative AI systems.
Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas
PDF ↗Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects, and prompting strategy) we evaluate the taxonomies as a classification task with the help of four language models (GPT-4.1-nano, Phi-4 14B, Qwen2.5-14B, Qwen3-14B). Our results show that fine-tuning is essential, since it transforms weak zero-shot baselines into competitive systems and reveals methodological differences that are hidden using base models. Across schemas, the Qwen models achieve the strongest overall performance, and Phi-4 14B consistently outperforms GPT-4.1-nano. Our hierarchical prompting method (HiPP), which predicts fine-grained techniques before aggregating them, is especially beneficial after fine-tuning and on the more ambiguous, low-agreement taxonomy, while remaining competitive on the simpler schema. The HQP dataset, annotated with the new intent-based labels, provides a richer lens on propaganda’s strategic goals and a challenging benchmark for future work on robust, real-world detection.