16 papers
Improving Scientific Document Retrieval with Academic Concept Index
Jeyun Lee, Junhyoung Lee, Wonbin Kweon +7
Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in voc…
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Rohan Surana, Gagan Mundada, Xunyi Jiang +19
Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajec…
Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
Bowen Jin, TJ Collins, Donghan Yu +10
Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs, motivating the design of multi-agent LLM systems where specialize…
Hybrid Latent Reasoning via Reinforcement Learning
Zhenrui Yue, Bowen Jin, Huimin Zeng +6
Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hid…
CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval
Runchu Tian, Xueqiang Xu, Bowen Jin +2
Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval resu…
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Bowen Jin, Hansi Zeng, Zhenrui Yue +5
Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLM…