Related papers: Orcust: Stepwise-Feedback Reinforcement Learning f…

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…

Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of…

Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative…

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…

In multi-hop question answering (MHQA) tasks, Chain of Thought (CoT) improves the quality of generation by guiding large language models (LLMs) through multi-step reasoning, and Knowledge Graphs (KGs) reduce hallucinations via semantic…

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance…

Graphical User Interface (GUI) action grounding is a critical step in GUI automation that maps language instructions to actionable elements on GUI screens. Most recent works of GUI action grounding leverage large GUI datasets to fine-tune…

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen…

GUI grounding aims to align natural language instructions with precise regions in complex user interfaces. Advanced multimodal large language models show strong ability in visual GUI grounding but still struggle with small or visually…

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with…

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a…

Online reinforcement learning (RL) with sparse rewards poses a challenge partly because of the lack of feedback on states leading to the goal. Furthermore, expert offline data with reward signal is rarely available to provide this feedback…

Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we…

Recent studies show that Large Language Models (LLMs) achieve strong reasoning capabilities through supervised fine-tuning or reinforcement learning. However, a key approach, the Process Reward Model (PRM), suffers from reward hacking,…

This paper presents an interpretable reward design framework for reinforcement learning based constrained optimal control problems with state and terminal constraints. The problem is formalized within a standard partially observable Markov…

A key challenge in training Vision-Language Model (VLM) agents, compared to Language Model (LLM) agents, lies in the shift from textual states to complex visual observations. This transition introduces partial observability and demands…

Mobile GUI agents excel at immediate reactive control but frequently fail in realistic, long-horizon tasks that require memory. This failure stems from a fundamental conflict between limited context windows and token-heavy screenshots. To…

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…