3 papers
cs.SE2026
VeriEvolve: Evaluator-First Evolution for Tool-Using Agents
Yueshen Li, Kamer Ali Yuksel, Gokhan Tur +2
A central obstacle to self-improving agents is the absence of a reliable fitness signal for realistic stateful tasks. We introduce \textsc{VeriEvolve}, an evaluator-first evolution…
cs.CL2026
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
Nimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur +1
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increas…
cs.LG2026
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
Emre Can Acikgoz, Cheng Qian, Jonas Hübotter +3
Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approa…