Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
Leon Engländer, Sophia Althammer, Ahmet Üstün +2
LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should naturally lead to a model e…
cs.LG2026
A Unified Framework for Rethinking Policy Divergence Measures in GRPO
Qingyuan Wu, Yuhui Wang, Simon Sinong Zhan +6
Reinforcement Learning with Verified Reward (RLVR) has emerged as a critical paradigm for advancing the reasoning capabilities of Large Language Models (LLMs). Most existing RLVR m…