Related papers: OS-Themis: A Scalable Critic Framework for General…

While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or…

While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine…

Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval, and has recently been advanced by reinforcement learning (RL) with outcome-based…

The rapid advancement of large Vision-Language Models (VLMs) has propelled the development of pure-vision-based GUI Agents, capable of perceiving and operating Graphical User Interfaces (GUI) to autonomously fulfill user instructions.…

With the aim of improving performance in Markov Decision Problem in an Off-Policy setting, we suggest taking inspiration from what is done in Offline Reinforcement Learning (RL). In Offline RL, it is a common practice during policy learning…

Reinforcement learning (RL) has driven recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be computed automatically, such as code generation. However, it is less effective in open-ended medical…

Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…

Reward models (RMs) play a critical role in aligning AI behaviors with human preferences, yet they face two fundamental challenges: (1) Modality Imbalance, where most RMs are mainly focused on text and image modalities, offering limited…

Reinforcement Learning (RL) is one of the most dynamic research areas in Game AI and AI as a whole, and a wide variety of games are used as its prominent test problems. However, it is subject to the replicability crisis that currently…

Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric…

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

Finetuning Large Vision-Language Models with reinforcement learning has emerged as a promising approach to enhance their capability in object-level grounding. However, existing methods, mainly based on GRPO, assign rewards at the response…

Reinforcement learning (RL) is one of the most active fields of AI research. Despite the interest demonstrated by the research community in reinforcement learning, the development methodology still lags behind, with a severe lack of…

Large language models have achieved strong performance on medical reasoning benchmarks, yet their deployment in clinical settings demands rigorous verification to ensure factual accuracy. While reward models offer a scalable approach for…

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference…

Bus holding control is a widely-adopted strategy for maintaining stability and improving the operational efficiency of bus systems. Traditional model-based methods often face challenges with the low accuracy of bus state prediction and…

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

We present THEMIS, a novel multi-task benchmark designed to comprehensively evaluate multimodal large language models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces…

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the visited states, e.g., a value function. Unfortunately, objectives of this type cannot model many real-world applications such as experiment design,…