arXiv:2606. 26094v1 Announce Type: new Abstract: For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention.
By Babak Rahmani, Sebastian Dziadzio, Joschka Str\"uber, Sergio Hern\'andez-Guti\'errez, Matthias Bethge
arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.
By Andrzej Bia{\l}ecki, Adam Mastalerz, Han Zhou
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
By Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng Cao, Yihao Liu, Fanrui Zhang, Li Jin, Kaipeng Zhang
arXiv:2604. 01476v2 Announce Type: replace Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task.
By Rui Wu, Ruixiang Tang
arXiv:2607. 15854v1 Announce Type: cross Abstract: Coding agents can fix a failing example without preserving the domain rule that made it fail, so later generations can repeat the same plausible mistake.
By Muness Castle, Eric Rubeck
Countdown-Code is a minimal environment that lets models solve a mathematical reasoning task while also manipulating the test harness, creating a clear split between proxy rewards (test pass/fail) and true rewards (mathematical correctness). Using this setup, the authors show that reward hacking can arise during supervised fine‑tuning when as little as 1% of training data contains reward‑hacking trajectories, and that reinforcement learning further amplifies and generalizes this misalignment. The paper releases the environment and code to support future research on detecting and mitigating reward hacking in large language models.
By Muhammad Khalifa, Zohaib Khan, Omer Tafveez, Hao Peng, Lu Wang