12 papers
MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents
Ruike Cao, Fanyu Zhao, Fugen Yao +6
The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over its response. Yet this capab…
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Jiangwang Chen, Zixin Song, Junlin Liu +10
Text-space optimization adapts large language models (LLMs) by editing external natural-language artifacts rather than model weights, so the optimized artifacts remain inspectable…
From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in Quark
Yanglong Song, Zihao Yang, Shuo Meng +6
Generative sequence models have shown strong results in recommendation. Applying them to search ranking is more challenging. Search behavior is inherently query-driven. Each query…
RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance
Hengjun Jiang, Liansheng Sun, Yan Jiang +6
Semantic relevance judgment for search is particularly challenging in knowledge-intensive scenarios, where accurate ranking requires not only semantic matching but also background…
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
Jiangwang Chen, Bowen Zhang, Zixin Song +4
Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they respond only after the user type…
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
Jiazheng Kang, Bowen Zhang, Zixin Song +4
ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to t…
RAVE: Re-Allocating Visual Attention in Large Multimodal Models
Xi Leng, Xinhong Ma, Ziqiang Dong +4
Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-moda…
ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression
Xiaojie Ke, Shuai Zhang, Liansheng Sun +6
Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its…
QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models
Yao Wu, Kangping Yin, Liang Dong +13
While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evalua…
Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning
Shijie Zhang, Xiang Guo, Rujun Guo +4
Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response…
ETR: Outcome-Guided Elastic Trust Regions for Policy Optimization
Shijie Zhang, Kevin Zhang, Zheyuan Gu +5
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success…
CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning
Shijie Zhang, Zheng Xiao, Shiyu Liu +7
Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still…