14 papers
Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertainty
Ziming Liu, Bhanu Chaitanya Jasti, Ziyang Xu +3
When a speaker refers to a scene that the listener cannot directly see, the listener must decide whether to preserve its current understanding or revise it as new utterances arrive…
Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents
Qi Liu, Yiqun Chen, Zidan Chen +6
Search agents now answer questions that take dozens of searches to settle, yet how such an agent reads a page has drawn far less attention than how it finds one. Nearly all of them…
Deep Research as Rubric for Reinforcement Learning
Wangyi Mei, Zhouhong Gu, Zhenhan Bai +9
Open-ended reasoning and long-form generation tasks lack reliable automatic verification signals for reward-based policy optimization. Rubrics offer a promising alternative, but ex…
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
Yiqun Chen, Wei Yang, Erhan Zhang +14
LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely op…
OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
Erhan Zhang, Yiqun Chen, Zechun Niu +6
Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewa…
Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents
Huyu Wu, Jun Liu, Xiaochi Wei +3
Self-evolving search agents reduce reliance on human-written training questions by generating and solving their own search tasks. We build on Search Self-Play (SSP), a representati…
Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
Jinyuan Feng, Xin Yu, Yiqun Chen +5
The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, current decoding strategies fa…
Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
Zixuan Yang, Yiqun Chen, Wei Yang +7
Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based metho…
Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
Ziyang Zeng, Heming Jing, Jindong Chen +11
Ranking relevance is a fundamental task in search engines, aiming to identify the items most relevant to a given user query. Traditional relevance models typically produce scalar s…
R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
Xiaowei Yuan, Lei Jin, Haoxin Zhang +6
Retrieval-augmented generation (RAG) plays a critical role in user-generated content (UGC) platforms, but its effectiveness critically depends on accurate query-document relevance…
SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation
Qian Dong, Jia Chen, Qingyao Ai +6
Existing retrieval-augmented code generation (RACG) methods typically use an external retrieval module to fetch semantically similar code snippets used for generating subsequent fr…
RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services
Fei Zhao, Chonggang Lu, Yue Wang +22
As a primary medium for modern information dissemination, social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform con…
PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval
Zihan Niu, Zheyong Xie, Shaosheng Cao +9
Social chatbots have become essential intelligent companions in daily scenarios ranging from emotional support to personal interaction. However, conventional chatbots with passive…
Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions
Jia Chen, Qian Dong, Haitao Li +9
User-generated content (UGC) communities, especially those featuring multimodal content, improve user experiences by integrating visual and textual information into results (or ite…