8 papers · 1 filter
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…
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…
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…
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…