Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Aditi Raghunathan

Aditi Raghunathan

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1NLP×1Crypto×1

Frequent co-authors

Chen Henry Wu1×
Ivan Bercovich1×
Ivgeni Segal1×
Kexun Zhang1×
Shashwat Saxena1×
Ziqian Zhong1×

Research Timeline

2026
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

The paper introduces Terminal Wrench, a comprehensive dataset of 331 reward-hackable terminal-agent environments and 3,632 exploit trajectories, demonstrating that detection of reward hacking degrades significantly when reasoning traces are removed.

Self-Trained Verification for Training- and Test-Time Self-Improvement

The paper proposes Self-Trained Verification (STV), a novel method that trains verifiers to catch self-generated errors by leveraging reference solutions, significantly boosting performance in both test-time refinement and training-time self-improvement.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CLRecentMay 28, 2026

Self-Trained Verification for Training- and Test-Time Self-Improvement

Chen Henry Wu, Aditi Raghunathan

The paper proposes Self-Trained Verification (STV), a novel method that trains verifiers to catch self-generated errors by leveraging reference solutions, significantly boosting performance in both te…

View →
cs.CRcs.AIRecentApr 19, 2026

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

Ivan Bercovich, Ivgeni Segal, Kexun Zhang, Shashwat Saxena +2 more

The paper introduces Terminal Wrench, a comprehensive dataset of 331 reward-hackable terminal-agent environments and 3,632 exploit trajectories, demonstrating that detection of reward hacking degrades…

View →