9 papers
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
Benlei Cui, Ruize Wang, Junjie Li +9
Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific informatio…
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
Yang Tian, Rui Wang, Xumeng Wen +5
Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide lim…
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference
Junjie Li, Jiong Lou, Jie Li
Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read bandwidth grow by orders of mag…
XekRung Technical Report
Jiutian Zeng, Junjie Li, Chengwei Dai +13
We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis p…
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
Junjie Li, Xinrui Guo, Yuhao Wu +3
What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain…
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Xumeng Wen, Zihan Liu, Shun Zheng +9
Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant int…