5 papers
What and Where in Identifying and Quantifying Conventions in Humans and AI Agents
Makoto Fukushima, Tim Puphal
Cooperative success rests in part on implicit communication. Partners converge on conventions: regularities that give an action meaning beyond its direct effect. Yet conventions ar…
Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL
Hanyu Wang, Nakul Agarwal, Hossein Nourkhiz Mahjoub +4
A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model in generating a trajectory…
Message capacity and claim wording set the transition points of collective truth-finding in language-model networks
Makoto Fukushima
Whether human or large language model (LLM), an agent in a discussion reads only a few of the others' contributions, bounded by cognition, context, or cost. LLM collectives can set…
The Convention Gap: Beyond Literal Content in Human-AI Cooperation
Makoto Fukushima, Hua-Dong Xiong, Ehsan Moradi Pari
Cooperative AI agents are often evaluated against other AIs, yet human cooperation is thought to rely on implicit conventions: shared rules for reading meaning beyond the literal m…
Advancements and limitations of LLMs in replicating human color-word associations
Makoto Fukushima, Shusuke Eshita, Hiroshige Fukuhara
Color-word associations play a fundamental role in human cognition and design applications. Large Language Models (LLMs) have become widely available and have demonstrated intellig…