相关论文: Hack-Verifiable Environments: Towards Evaluating R…

With advances in generative AI, there is now potential for autonomous agents to manage daily tasks via natural language commands. However, current agents are primarily created and tested in simplified synthetic environments, leading to a…

Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run…

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations in a lack of external feedback, these agents struggle with…

Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and exploit acquired…

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…

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…

Reward hacking in code generation, where models exploit evaluation loopholes to obtain full reward without correctly solving the tasks, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models.…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…

One of the main research areas in Artificial Intelligence is the coding of agents (programs) which are able to learn by themselves in any situation. This means that agents must be useful for purposes other than those they were created for,…

Deploying deep reinforcement learning in safety-critical settings requires developing algorithms that obey hard constraints during exploration. This paper contributes a first approach toward enforcing formal safety constraints on end-to-end…

As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent's performance and correctness. In this paper we formalize and theoretically…

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models (MLLMs) toward human-preferred behaviors. However, these…

AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can…

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also…

Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and increasingly rely on marketplaces to mediate access to models, tools, and data, making competition between systems…

Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or faithfully solving the intended problem. We study this phenomenon in a generic machine…