arXiv AI June 26, 2026 By Binghai Wang, Chenlong Zhang, Dayiheng Liu, Jiajun Zhang, Jiawei Chen, Mouxiang Chen, Rongyao Fang, Siyuan Zhang, Xuwu Wang, Yuheng Jing, Zeyao Ma, Zeyu Cui

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Read the original on arXiv AI →

arXiv:2606. 26300v1 Announce Type: new Abstract: A classical intuition holds that verifying a solution is easier than producing one.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 30

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.

By Pei-Chi Pan, Yingbin Liang, Sen Lin

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Aug 11

From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering

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

llms reinforcement-learning robotics

arXiv AI

Jun 16

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

arXiv:2606. 15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety.

By \"Omer Veysel \c{C}a\u{g}atan, Xuandong Zhao

llms agents reinforcement-learning safety

arXiv AI

Jun 9

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

arXiv:2606. 07682v1 Announce Type: cross Abstract: AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments.

By Rishi Desai, Jesse Hu, Joan Cabezas, Neel Harsola, Pratyush Shukla, Roey Ben Chaim, Adnan El Assadi, Omkaar Mukund Kamath, Fenil Faldu, Prannay Hebbar, Jiankai Sun, Yiyuan Li, Pramod Srinivasan, Ishan Gupta, Christopher Settles, Daniel Wang, Derek Chen, Pranav Raja, Albert Liu, Marek \v{S}uppa, Nevasini Sasikumar, Luyang Kong, Erik Quintanilla, Xiangyi Li, Ivan Bercovich, Steven Dillmann

agents benchmarks safety

arXiv AI

Jul 13

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

arXiv:2607. 08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks.

By Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ninghao Liu, Lichao Sun, Haotao Mi, LeoweiLiang

agents multimodal benchmarks

arXiv AI

Jul 2

Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations

arXiv:2607. 01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning.

By Mehul Damani, Isha Puri, Idan Shenfeld, Jacob Andreas

reinforcement-learning fine-tuning benchmarks safety

Related stories

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations