paper-with-me

Papers

Scalable agent alignment via reward modeling: a research direction

2018-11-19 · Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg

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 objective. This gives rise to the agent alignment problem: how do we create agents that behave in accordance with the user's intentions? We outline a high-level research direction to solve the agent alignment problem centered around reward modeling: learning a reward function from interaction with the user and optimizing the learned reward function with reinforcement learning. We discuss the key challenges we expect to face when scaling reward modeling to complex and general domains, concrete approaches to mitigate these challenges, and ways to establish trust in the resulting agents.

📄 PDF Abstract BibTeX arXiv:1811.07871

Code (3)

Angeliki-Panoulia/CallForCode
rddy/ReQueST tf
rgreenblatt/ai_alignment_readings

Tasks

Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward

2022-10-09 · Zixian Ma, Rose Wang, Li Fei-Fei, Michael Bernstein 외

Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not readily available in the real world. Current m…

Multi-agent Reinforcement Learning

Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs

2026-03-11 · Panatchakorn Anantaprayoon, Nataliia Babina, Nima Asgharbeygi, Jad Tarifi arxiv

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment ob…

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

2025-10-09 · Tianci Liu, Ran Xu, Tony Yu, Ilgee Hong 외 arxiv

Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preference…

Reinforcement Learning

Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment

2025-12-05 · Panatchakorn Anantaprayoon, Nataliia Babina, Jad Tarifi, Nima Asgharbeygi arxiv

Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI systems progress toward Artificial Genera…

Reward Modeling for Multi-Agent Orchestration

2026-06-11 · King Yeung Tsang, Zihao Zhao, Vishal Venkataramani, Haizhou Shi 외 arxiv

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational …

Mathematical ReasoningQuestion Answering