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
论文检索
输入标题、作者或关键词，从 9,460 篇学术成果中精准定位
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.
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
PDF ↗While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning data. To address this issue, existing approaches typically distill chain-of-thought reasoning traces from large proprietary models via supervised fine-tuning, then conduct reinforcement learning (RL). These methods exhibit limited improvement on underrepresented domains like rare diseases while incurring substantial costs from generating complex reasoning chains. To efficiently enhance medical reasoning, we propose MedSSR, a Medical Knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework. Our framework first employs rare disease knowledge to synthesize distribution-controllable reasoning questions. We then utilize the policy model itself to generate high-quality pseudo-labels. This enables a two-stage, intrinsic-to-extrinsic training paradigm: self-supervised RL on the pseudo-labeled synthetic data, followed by supervised RL on the human-annotated real data. MedSSR scales model training efficiently without relying on costly trace distillation. Extensive experiments on Qwen and Llama demonstrate that our method outperforms existing methods across ten medical benchmarks, achieving up to **+5.93%** gain on rare-disease tasks. Our code is available at https://github.com/tdlhl/MedSSR.
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
PDF ↗Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter scalability and computational efficiency. However, low-resource language tokens are often routed to different experts than those predominantly activated by high-resource inputs, which limits cross-lingual expert sharing. This cross-lingual routing divergence consequently hinders their efficacy in multilingual contexts. To address this issue, we propose SARA (Semantically Anchored Routing Alignment), a framework designed to transfer specialized capabilities from high-resource languages as anchors to low-resource languages. SARA explicitly aligns the routing distribution of multilingual inputs with high-resource semantic anchors using a symmetric Jensen-Shannon (JS) divergence constraint. Unlike traditional distillation methods that operate on output logits, SARA directly aligns the internal routing distributions of MoE layers, encouraging mechanistic consistency in expert selection across languages. We conduct experiments on 2 LLMs across 5 low-resource languages and 3 benchmarks. Experiment results demonstrate that SARA outperforms standard instruction tuning (e.g., +0.8% on Qwen3-30B-A3B and +1.2% on Phi-3.5-MoE-instruct on Global-MMLU benchmark). Further analyses show that SARA effectively addresses performance bottlenecks in low-resource languages, providing a scalable pathway to enhance multilingual capabilities in sparse architectures.
Reliable interpretation of multimodal dental data is essential for automated oral healthcare, yet current multimodal large language models (MLLMs) show limited understanding of dental images. Although complex reasoning improves performance, its gains in dentistry are substantially smaller than in other medical domains, suggesting that complex reasoning is not yet sufficiently incentivized for dental diagnosis, likely due to insufficient domain knowledge and limited reinforcement learning on dental questions. We present DentalGPT, a dentistry-specialized MLLM trained via staged multimodal alignment and reinforcement learning. By constructing the largest annotated multimodal dental dataset to date with over 120k images, multimodal alignment provides the necessary domain knowledge foundation to support and incentivize complex reasoning, which is further strengthened through reinforcement learning. Experiments on expert-annotated benchmarks and dental subsets of medical VQA benchmarks show that DentalGPT achieves superior performance on disease classification and dental VQA tasks, outperforming many state-of-the-art MLLMs despite its compact 7B parameter scale.
Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing evaluation benchmarks include few requirement types and writing reward models are not evaluated. In terms of training, existing studies often enhance writing ability through reinforcement learning with verifiable rewards (RLVR). Howerver, existing reward model training remains coarse-grained. To address these issues, we introduce W²Bench, a comprehensive evaluation benchmark, and WRL, a fine-grained training framework. W²Bench covers five task categories and seven requirement types, enabling systematic evaluation of both writing and writing reward models by measuring the correlation between reward rankings and golden rankings. WRL constructs positive and negative samples by dropping instruction requirements to construct positive and negative examples, allowing more precise reward model training. Experiments show that our models achieve substantial improvements on various writing benchmarks and exhibit strong generalization. We will release our code and data to support future research.
While LLMs demonstrate impressive reasoning capabilities, their internal decision dynamics remain opaque. To render these process interpretable and intervenable, we propose Dynamic Entropy Tracing, a mechanism-aware framework that interprets the evolving "choice state" of attention heads during CoT generation through stepwise head-wise option-logit and entropy tracing. Our analysis reveals distinct functional behaviors at attention heads: Steadfast Heads, characterized by consistently low entropy and producing a sharp, option-selective logit pattern with a stable top choice, and Wavering Heads, characterized by consistently high entropy and producing flat or oscillatory option logits without a persistent winner. Leveraging these traces, we identify a set of intervention targets and perform Selective Head Fine-Tuning, updating solely these selected heads against a frozen backbone. Experiments across the LLaMA and Qwen families reveal a striking plasticity hierarchy: fine-tuning just 30 Wavering Heads recovers over 98% of the performance achieved by full-parameter tuning, and in some settings modestly exceeds it. In contrast, intervening on Steadfast Heads yields much less gains. Our findings translate process-level mechanistic observables into a principled criterion for selective fine-tuning, offering a fundamental insight: the most effective tuning knobs are not the components that signal the final decision, but those that retain uncertainty, and thus plasticity, during its formation.
Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However, they exhibit limited exploration due to reliance on on-policy rollouts which are confined to the current policy’s distribution, resulting in narrow trajectory diversity. Recent approaches attempt to expand policy coverage by incorporating trajectories generated from stronger expert models, yet this reliance increases computational cost and such advanced models are often inaccessible. To address these issues, we propose In-Context Steered Policy Optimization (ICPO), a unified framework that leverages the inherent in-context learning capability of LRMs to provide expert guidance using existing datasets. ICPO introduces mixed-policy GRPO with implicit expert forcing, which expands exploration beyond the current policy distribution without requiring advanced LRM trajectories. To further stabilize optimization, ICPO integrates expert region reject sampling to filter unreliable off-policy trajectories and annealed expert-bonus reward shaping to balance early expert guidance with later autonomous improvement. Results demonstrate that ICPO consistently enhances RLVR performance and training stability on mathematical reasoning benchmarks, revealing a scalable and effective RLVR paradigm for LRMs. Our code is available at https://github.com/Celine-hxy/ICPO.
AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent
PDF ↗Lossless compression has made significant advancements in Genomics Data (GD) storage, sharing and management. Current learning-based methods are non-evolvable with problems of low-level compression modeling, limited adaptability, and user-unfriendly interface. To this end, we propose AgentGC, the first evolutionary Agent-based GD Compressor, consisting of 3 layers with multi-agent named Leader and Worker. Specifically, the 1) User layer provides a user-friendly interface via Leader combined with LLM; 2) Cognitive layer, driven by the Leader, integrates LLM to consider joint optimization of algorithm-dataset-system, addressing the issues of low-level modeling and limited adaptability; and 3) Compression layer, headed by Worker, performs compression decompression via a automated multi-knowledge learning-based compression framework. On top of AgentGC, we design 3 modes to support diverse scenarios: CP for compression-ratio priority, TP for throughput priority, and BM for balanced mode. Compared with 14 baselines on 9 datasets, the average compression ratios gains are 16.66%, 16.11%, and 16.33%, the throughput gains are 4.73x, 9.23x, and 9.15x, respectively.
Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsistent, with topic drift, repetitive chitchat, and mismatched answer formats across turns. We address this from a data selection perspective and propose MDS (Multi-turn Dialogue Selection), a dialogue-level framework that scores whole conversations rather than isolated turns. MDS combines a global coverage stage that performs bin-wise selection in the user-query trajectory space to retain representative yet non-redundant dialogues, with a local structural stage that evaluates within-dialogue reliability through entity-grounded topic grounding and information progress, together with query-answer form consistency for functional alignment. MDS outperforms strong single-turn selectors, dialogue-level LLM scorers, and heuristic baselines on three multi-turn benchmarks and an in-domain Banking test set, achieving the best overall rank across reference-free and reference-based metrics, and is more robust on long conversations under the same training budget. Code and resources are included in the supplementary materials.
Existing benchmarks treat multi-turn conversation and reasoning-intensive retrieval separately, yet real-world information seeking requires both. To bridge this gap, we present a benchmark for reasoning-based conversational information retrieval comprising 707 conversations (2,971 turns) across eleven domains. To ensure quality, our Decomposition-and-Verification framework transforms complex queries into fact-grounded multi-turn dialogues through multi-level validation, where atomic facts are verified against sources and explicit retrieval reasoning is generated for each turn. Comprehensive evaluation reveals that combining conversation history with reasoning doubles retrieval performance (Baseline .236 \rightarrow History+Reasoning .479 nDCG@10), while reasoning-specialized models substantially outperform dense encoders. Despite these gains, further analysis highlights that implicit reasoning remains challenging, particularly when logical connections are not explicitly stated in the text. [<https://github.com/RECOR-Benchmark/RECOR>]
Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory mechanisms, such accumulation disrupts logical continuity and undermines task alignment. This positions memory not as an auxiliary efficiency concern, but as a core component for sustaining coherent, goal-directed reasoning over long horizons.We propose MemoBrain, an executive memory model for tool-augmented agents that constructs a dependency-aware memory over reasoning steps, capturing salient intermediate states and their logical relations. Operating as a co-pilot alongside the reasoning agent, MemoBrain organizes reasoning progress without blocking execution and actively manages the working context. Specifically, it prunes invalid steps, folds completed sub-trajectories, and preserves a compact, high-salience reasoning backbone under a fixed context budget. Together, these mechanisms enable explicit cognitive control over reasoning trajectories rather than passive context accumulation.We evaluate MemoBrain on challenging long-horizon benchmarks, including GAIA, WebWalker, and BrowseComp-Plus, demonstrating consistent improvements over strong baselines.
Live-stream E-commerce faces significant challenges from morphs, deliberate linguistic variants used to evade real-time voice filters and amplify product claims illegally. While critical for regulatory enforcement, Live Auditory Morph Resolution (LiveAMR) research is hindered by limited datasets: prior work relied on narrow, redundant health domain corpora, restricting model robustness. To bridge this gap, we introduce two datasets: (1) HealthAMR, a refined health-domain corpus via deduplication and re-annotation. (2) GeneralAMR, a general domain benchmark with 28K annotated sentences from 77 channels across 7 E-commerce categories. Further, we propose JointMRE, a multi-task framework that jointly resolves morphs and generates structured explanations, transferring grammatical insights from large language models to enhance generalization. Predictions are refined by our Conflict-aware Dual-output Refinement Framework (CDRF), which detects inconsistencies between corrections and explanations. Experiments show CDRF significantly improves morph resolution accuracy and interpretability. Our datasets and code are available [<https://anonymous.4open.science/r/Morph-Resolution-Datasets-and-Methods-611E>].
Recent work on music question answering (Music-QA) has primarily focused on single-track understanding, where models answer questions about an individual audio clip using its tags, captions, or metadata. However, listeners often describe music in comparative terms, and existing benchmarks do not systematically evaluate reasoning across multiple tracks. Building on the Jamendo-QA dataset, we introduce Jamendo-MT-QA, a dataset and benchmark for multi-track comparative question answering. From Creative Commons-licensed tracks on Jamendo, we construct 36,519 comparative QA items over 12,173 track pairs, with each pair yielding three question types: yes/no, short-answer, and sentence-level questions. We describe an LLM-assisted pipeline for generating and filtering comparative questions, and benchmark representative audio-language models using both automatic metrics and LLM-as-a-Judge evaluation.
Earth Observation (EO) provides critical planetary data for environmental monitoring, disaster management, climate science, and other scientific domains. In this work we ask: Are AI systems ready for reliable Earth Observation? To answer this, we introduce **UnivEARTH**, a coding benchmark of 408 yes/no questions from NASA Earth Observatory articles across 7 various topics and over 15 satellite instruments and sources. Using Google Earth Engine API as a tool in a zero-shot setup, LLM agents achieve an accuracy of 40.0% where the code fails to run over 44% of the time. To better understand LLM agent behavior, we also analyze the impact of using the JavaScript API versus Python and the effect of providing documentation. Furthermore, we find that using a reflexion framework significantly reduces errors: Claude-4.5-Sonnet, Gemini-2.5-Pro, and GPT-5 accuracies rise to around 60%. However, these results remain only marginally above random chance. Taken together, our findings identify significant challenges to be solved before AI agents can automate earth observation, and suggest paths forward.