15 papers
ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
Zhilin Wang, Jaehun Jung, Ximing Lu +7
Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and s…
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Fang Wu, Weihao Xuan, Heli Qi +4
Although RLVR has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands…
RLP: Reinforcement as a Pretraining Objective
Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye +5
The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful…
MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
Zexue He, Yu Wang, Churan Zhi +11
Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversat…
iGRPO: Self-Feedback-Driven LLM Reasoning
Ali Hatamizadeh, Shrimai Prabhumoye, Igor Gitman +5
Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions. Reinforcement Le…
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Ximing Lu, David Acuna, Jaehun Jung +12
Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked b…