5 papers · 1 filter
Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents
Zhipeng Qian, Zihan Liang, Yufei Ma +10
A central limitation of current data-free self-evolution methods for training search agents is their reliance on difficulty-based proposer rewards. These methods reward a proposer…
Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning
Zihan Liang, Yufei Ma, Ben Chen +4
Post-training has become the dominant recipe for turning a language model into a competent search-augmented reasoning agent. A line of recent work pushes its performance further by…
SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain
Lingtao Mao, Huangyu Dai, Xinyu Sun +4
Multimodal large language models are increasingly used as agent backbones that understand multimodal inputs, plan retrieval actions, invoke external tools, and reason over retrieve…
SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
Yufei Ma, Zihan Liang, Ben Chen +6
Search-augmented reasoning agents interleave internal reasoning with calls to an external retriever, and their performance relies on the quality of each issued query. However, unde…
IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
Zihan Liang, Yufei Ma, Ben Chen +6
Reinforcement learning has emerged as an effective paradigm for training large language models to perform search-augmented reasoning. However, existing approaches rely on trajector…