5 papers
Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling
Yuchen Liu, Yingjie Feng, Lixiong Qin +5
In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on co…
VSPO: Vector-Steered Policy Optimization for Behavioral Control
Xuechen Zhang, Zijian Huang, Kai Yang +3
Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level…
SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
Xuechen Zhang, Koustava Goswami, Samet Oymak +2
Retrieval-augmented generation (RAG) has strong potential for producing accurate and factual outputs by combining language models (LMs) with evidence retrieved from large text corp…
BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
Xuechen Zhang, Zijian Huang, Yingcong Li +3
Small language models (SLMs) struggle to learn complex reasoning behaviors, especially when high-quality traces are scarce or difficult to learn from. The standard training approac…
Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement
Xuechen Zhang, Zijian Huang, Chenshun Ni +3
Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and h…