William Yang

The limits of attempted equity within a capitalist economy have been reached, and any pro-social solution cannot just be legislative tweaks and ought to be transformative in nature.

Abstract: The proliferation of LLM-based agents has led to increasing deployment of inter-agent collaboration for tasks like scheduling, negotiation, resource allocation etc.

Abstract: We introduce LEDOM, the first purely reverse language model, trained autoregressively on 435B tokens with 2B and 7B parameter variants, which

Jolanta Bernatoniene MD, PhD [email protected] ∙ Mélisande Bourgoin-Heck MD ∙ Mauro Cancian MD

Abstract: Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical

Abstract: Scaling test-time computation improves performance across different tasks on large language models (LLMs), which has also been extended to tool-augmented agents.

Abstract: The mechanism by which RL contributes to reasoning capabilities-whether it incentivizes the synthesis of new skills or merely amplifies existing behaviors-remains a subject of intense debate.

Abstract: Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development.