4 papers · 1 filter
AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
Liqin Ye, Rongzhi Zhang, Xin Liu +5
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) fore…
STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules
Ranajoy Sadhukhan, Euijin Hong, Sheng Cao +9
Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures remains expensive and data-h…
Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards
Cheng Jiayang, Xin Liu, Zhihan Zhang +8
Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workfl…
HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
Weiqi Wang, Xin Liu, Binxuan Huang +13
RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts…