12 papers
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Wenhan Ma, Jianyu Wei, Liang Zhao +10
Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains…
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
Xinbo Xu, Ruihan Yang, Haiyang Shen +13
Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing…
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
Shuzheng Si, Haozhe Zhao, Cheng Gao +11
Teaching large language models (LLMs) to be faithful in the provided context is crucial for building reliable information-seeking systems. Therefore, we propose a systematic framew…
SCI-Reason: A Dataset with Chain-of-Thought Rationales for Complex Multimodal Reasoning in Academic Areas
Chenghao Ma, Haihong E., Junpeng Ding +7
Large Language Models (LLMs) and Large Multimodal Models (LMMs) demonstrate impressive problem-solving skills in many tasks and domains. However, their ability to reason with compl…
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Zefan Cai, Yichi Zhang, Bofei Gao +8
In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Ou…