Tootfinder

Für die breite Verwendung von #KI, speziell im Kontext #Schule, muss sichergestellt sein, dass #LLMs user:innen nicht zu selbstgefährdendem Verhalten animieren.
Das Nonprofit Transluce arbeitet an verschie…

Surfacing Pathological Behaviors in Language Models
We train reinforcement learning (RL) agents to craft realistic natural-language prompts that elicit specified behaviors in frontier open-weight models (Llama 3.1/4, Qwen 2.5, and DeepSeek-V3), using a proposed variational lower bound to guide the search.

Another of my forays into AI ethics is just out! This time the focus is on the ethics (or lack thereof) of Reinforcement Learning Feedback (RLF) techniques aimed at increasing the 'alignment' of LLMs.
The paper is fruit of the joint work of a great team of collaborators, among whom @… and @…

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback - Ethics and Information Technology
This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback methods, involving either human feedback (RLHF) or AI feedback (RLAIF). Specifically, we show the shortcomings of the broadly pursued alignment goals of honesty, harmlessness, and helpfulness. Through a multidisciplinary sociotechnical critique, we examine both the theoretical underpinni…

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning
Maxime Toquebiau, Jae-Yun Jun, Fa\"iz Benamar, Nicolas Bredeche
https://arxiv.org/abs/2506.05236

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning
Communication is a fundamental aspect of coordinated behavior in multi-agent reinforcement learning. Yet, most prior works in this field have focused on emergent communication protocols developed from scratch, often resulting in inefficient or non-interpretable systems. Inspired by the role of language in natural intelligence, we investigate how grounding agents in a human-defined language can improve learning and coordination of multiple embodied agents. We propose a framework in which agents …

This https://arxiv.org/abs/2506.01016 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Optimistic critics can empower small actors
Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of asymmetric setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, sm…

This https://arxiv.org/abs/2501.09622 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Optimizing hypergraph product codes with random walks, simulated annealing and reinforcement learning
Hypergraph products are quantum low-density parity-check (LDPC) codes constructed from two classical LDPC codes. Although their dimension and distance depend only on the parameters of the underlying classical codes, optimizing their performance against various noise channels remains challenging. This difficulty partly stems from the complexity of decoding in the quantum setting. The standard, ad hoc approach typically involves selecting classical LDPC codes with large girth. In this work, we fo…

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
Keyu Zhao, Fengli Xu, Yong Li
https://arxiv.org/abs/2506.05069 ht…

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation
Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interp…

Autonomous Vehicle Lateral Control Using Deep Reinforcement Learning with MPC-PID Demonstration
Chengdong Wu, Sven Kirchner, Nils Purschke, Alois C. Knoll
https://arxiv.org/abs/2506.04040

Autonomous Vehicle Lateral Control Using Deep Reinforcement Learning with MPC-PID Demonstration
The controller is one of the most important modules in the autonomous driving pipeline, ensuring the vehicle reaches its desired position. In this work, a reinforcement learning based lateral control approach, despite the imperfections in the vehicle models due to measurement errors and simplifications, is presented. Our approach ensures comfortable, efficient, and robust control performance considering the interface between controlling and other modules. The controller consists of the conventi…

This https://arxiv.org/abs/2505.23703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability
Enhancing the mathematical reasoning capabilities of LLMs has garnered significant attention in both the mathematical and computer science communities. Recent works have made substantial progress in both Natural Language (NL) reasoning and Formal Language (FL) reasoning by leveraging the potential of pure Reinforcement Learning (RL) methods on base models. However, RL approaches struggle to impart new capabilities not presented in the base model, highlighting the need to integrate more knowledg…

This https://arxiv.org/abs/2505.23585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

On-Policy RL with Optimal Reward Baseline
Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability due to loose on-policy constraints and computational inefficiency due to auxiliary models. In this work, we propose On-Policy RL with Optimal reward baseline (OPO), a novel and simplified reinforcement learning algorithm designed to address these challenges. O…

CORA: Coalitional Rational Advantage Decomposition for Multi-Agent Policy Gradients
Mengda Ji, Genjiu Xu, Liying Wang
https://arxiv.org/abs/2506.04265 http…

CORA: Coalitional Rational Advantage Decomposition for Multi-Agent Policy Gradients
This work focuses on the credit assignment problem in cooperative multi-agent reinforcement learning (MARL). Sharing the global advantage among agents often leads to suboptimal policy updates as it fails to account for the distinct contributions of agents. Although numerous methods consider global or individual contributions for credit assignment, a detailed analysis at the coalition level remains lacking in many approaches. This work analyzes the over-updating problem during multi-agent policy…