5 papers
Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents
Han Chi, Jiaxin Qi, Yan Cui +2
Rapid advances in large language models have improved the task-solving capabilities of command-line-interface (CLI)-based agents, whose CLIs determine how models invoke tools, main…
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
Wenjian Zhang, Kongcheng Zhang, Jiaxin Qi +2
Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still…
Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
Kongcheng Zhang, Qi Yao, Shunyu Liu +7
Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improve…
Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
Kongcheng Zhang, Qi Yao, Shunyu Liu +5
Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits…
Reasoning with Reinforced Functional Token Tuning
Kongcheng Zhang, Qi Yao, Baisheng Lai +5
In this work, we propose Reinforced Functional Token Tuning (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with self-play learn-to-reas…