15 papers
Repo2Skill-Evo: Repository Skills Go Stale in Silence
Chenyuan Duan, Ge Shi, Zineng Mao +10
Large language model (LLM) agents increasingly operate over evolving software repositories, where success depends on repository-specific procedural knowledge: which APIs to call, w…
CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs
Zihan Nan, Yang Gu, Wei Liu +4
Tabular data processing is central to data work, and LLM-based assistants have recently shown promising capabilities in supporting such tasks. However, existing benchmarks primaril…
WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing
Hao Liang, Meiyi Qiang, Sizhe Qiu +2
Enterprise agents often need to integrate heterogeneous knowledge sources: documents for narrative facts, tables for computation, and dependency graphs for file relationships. Exis…
AgentOmnia: Scaling Agentic Models for Full-Scenario Applications
Hao Jiang, Gangtao Xin, Yingdi Huang +35
Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings. We frame this as full-sc…
OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios
Chengyu Shen, Yujie Fu, Gangtao Xin +13
Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tas…
ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows
Wei Liu, Yang Gu, Xi Yan +5
Table processing-including cleaning, transformation, augmentation, and matching-is a foundational yet error-prone stage in real-world data pipelines. While recent LLM-based approac…
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
Kaixin Zhu, Yiwen Tang, Yifan Yang +9
High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass…
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
Zeli Su, Ziyin Zhang, Zhou Liu +7
Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in…
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Dongsheng Ma, Jiayu Li, Zhengren Wang +10
Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting ev…
Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
Zijun Shen, Sihan Yang, Ruichuan An +5
Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token…
FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
Qijie You, Hao Liang, Mingrui Chen +4
As video becomes increasingly central to information dissemination and multimodal large language models (MLLMs) continue to advance, evaluating video retrieval has become increasin…
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
Zhengyang Zhao, Lu Ma, Wentao Zhang
Inference-time harnesses substantially improve large language models on complex reasoning tasks. However, the intrinsic capabilities of the underlying model remain unchanged by the…
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
Hao Liang, Qihan Lin, Zhaoyang Han +7
Large language models are increasingly used in K-12 education, but existing benchmarks mainly test exam question answering rather than understanding how curriculum knowledge is str…
Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
Lingzhuang Sun, Yuxia Zhu, Ruitong Liu +10
While Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), relying solely on linear text sequences re…
Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision
Lingzhuang Sun, Ruitong Liu, Yuxia Zhu +5
Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevailing par…