Agents
Mars: Situated Inductive Reasoning in an Open-World Environment Xiaojuan Tang
Large Language Models (LLMs) trained on massive corpora have shown remarkable success in knowledge-intensive tasks. Y et, most of them rely on pre-stored knowledge. Inducing new general knowledge from a specific environment and performing reasoning with the acquired knowledge-- situated inductive reasoning, is crucial and challenging for machine intelligence. In this paper, we design Mars, an interactive environment devised for situated inductive reasoning. It introduces counter-commonsense game mechanisms by modifying terrain, survival setting and task dependency while adhering to certain principles.
Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
As AI systems become increasingly sophisticated and interconnected, it will be critical that they be competent at cooperating, both with other AI systems and with humans.
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery Alex Rutherford Michael Beukman Timon Willi Bruno Lacerda Nick Hawes Jakob Foerster University of Oxford
Put differently, current methods fail to predict intuitive measures of "learnability."
Observational Scaling Laws and the Predictability of Language Model Performance
Self-Consistency as language model capabilities continue to improve.
Can Large Language Model Agents Simulate Human Trust Behavior?
In addition, we probe the biases of agent trust and differences in agent trust towards other LLM agents and humans.
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning Hao Ma
Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms are effective in general RL settings, they often exhibit suboptimal performance and vulnerability to distribution collapse when applied to the fine-tuning of LLMs.
ProgressGym: Alignment with a Millennium of Moral Progress
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic moral practices on a broad scale. We introduce progress alignment as a technical solution to mitigate this imminent risk. Progress alignment algorithms learn to emulate the mechanics of human moral progress, thereby addressing the susceptibility of existing alignment methods to contemporary moral blindspots.