SS
Shashwat Saxena
cs.AIcs.LGcs.CRcs.MAcs.ROcs.CL
On Valency
published · living versionsW_8y7sx4am·v1 · currentpublished
VaDar: Implicit Goal Conditioning via Value Disaggregation
with Mehul Goel, Sreyas Venkataraman, Sarvesh Patil, Max Simchowitz
1 version
Preprints & journals
7 papers in the corpus · 2025–2026VaDar: Implicit Goal Conditioning via Value Disaggregation2610.26629v1 · Shashwat Saxena, Mehul Goel, Sreyas Venkataraman et al.2026 · 0 citationsarXivon Valency
Scalable Weak-to-Strong Verifier Hardening for Agent Environments2610.15924v1 · Chong Zeng, Ziqian Zhong, Kexun Zhang et al.2026 · 0 citationsarXiv
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops2606.08960v1 · Ziqian Zhong, Ivgeni Segal, Ivan Bercovich et al.2026 · 0 citationsarXiv
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies2605.03065v4 · Sarvesh Patil, Mitsuhiko Nakamoto, Manan Agarwal et al.2026 · 0 citationsarXiv
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories2604.17596v1 · Ivan Bercovich, Ivgeni Segal, Kexun Zhang et al.2026 · 0 citationsarXiv
Hodoscope: Unsupervised Monitoring for AI Misbehaviors2604.11072v1 · Ziqian Zhong, Shashwat Saxena, Aditi Raghunathan2026 · 0 citationsarXiv
Jailbreaking in the Haystack2511.04707v2 · Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena et al.2025 · 0 citationsarXiv
Career total: 7 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.