Related papers: Interactive Critique-Revision Training for Reliabl…

Aviation training is a core link in ensuring flight safety, improving industry efficiency and promoting sustainable development. It not only involves flight simulation but also requires the learning of a great deal of professional aviation…

Traditionally, AI development for two-player zero-sum games has relied on two primary techniques: decision trees and reinforcement learning (RL). A common approach involves using a fixed decision tree as one player's strategy while training…

Recent reinforcement learning approaches, such as outcome-supervised GRPO, have advanced Chain-of-Thought reasoning in large language models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) is unexplored. To address the lack of…

Offline reinforcement learning agents face significant deployment challenges due to the synthetic-to-real distribution mismatch. While most prior research has focused on improving the fidelity of synthetic sampling and incorporating…

We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via a generalized duality. DuPO addresses two key limitations: Reinforcement Learning with Verifiable Rewards (RLVR)'s reliance…

Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is…

Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a reinforcement learning-augmented LLM agent framework that…

GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to brittle optimization behavior, as global importance-ratio…

Group Relative Policy Optimization (GRPO) has demonstrated wide adoption in the post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and preferred behaviour is learnt via reinforcement learning. Owing to…

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment…

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Large language models (LLMs) exhibit varying levels of confidence across input prompts (questions): some lead to consistent, semantically similar answers, while others yield diverse or contradictory outputs. This variation reflects LLM's…

Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM)-based AI agents. However, existing backbone RL algorithms lack verified convergence guarantees in agentic scenarios, especially in…

In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems…

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Large language model (LLM) agents that follow the sequential "reason-then-act" paradigm have achieved superior performance in many complex tasks.However, these methods suffer from limited exploration and incomplete environmental…

Reinforcement Learning from Human Feedback (RLHF) has been highly successful in aligning large language models with human preferences. While prevalent methods like DPO have demonstrated strong performance, they frame interactions with the…

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…