13 papers
Schedule-Level Shared-Prefix Reuse for LLM RL Training
Pengbo Li, Feiyuan Zhang, Guangming Sheng +7
GRPO-based LLM post-training commonly samples multiple trajectories from the same prompt and then trains on the resulting group. In long-context GRPO workloads, this shared prompt-…
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
Yaorui Shi, Shugui Liu, Yu Yang +7
Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as t…
Denoising Neural Reranker for Recommender Systems
Wenyu Mao, Shuchang Liu, Hailan Yang +9
For multi-stage recommenders in industry, a user request would first trigger a simple and efficient retriever module that selects and ranks a list of relevant items, then the recom…
Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging
Jiabei Liu, Wenyu Mao, Junfei Tan +4
Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for…
R^2-Mem: Reflective Experience for Memory Search
Xinyuan Wang, Wenyu Mao, Junkang Wu +2
Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing dee…
Joint Optimization of Multi-agent Memory System
Wenyu Mao, Haoyang Liu, Haosong Tan +4
Memory systems are critical for LLMs, mitigating context window limitations and supporting long-horizon user-LLM interactions. Such systems typically comprise multiple agents respo…