9 papers · 1 filter
DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning
Yu Wang, Ming Fan, Xicheng Zhang +5
Chain-of-thought (CoT) supervision exposes intermediate rationales, but flat rationale targets usually optimize a single reasoning sequence and provide limited supervision on how l…
ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents
Zhuofeng Li, Yi Lu, Dongfu Jiang +7
The rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support. However, LLM-based reviewers often generate s…
CocoaBench: Evaluating Unified Digital Agents in the Wild
CocoaBench Team, Shibo Hao, Zhining Zhang +29
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly int…
RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game
Shijia Xu, Yu Wang, Xiaolong Jia +3
Despite the widespread adoption of Large Language Models (LLMs) in Legal AI, their utility for automated contract revision remains impeded by hallucinated safety and a lack of rigo…
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
Shijia Xu, Zhou Wu, Xiaolong Jia +3
Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reaso…
DLLM Agent: See Farther, Run Faster
Huiling Zhen, Weizhe Lin, Renxi Liu +15
Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for…