activity
20242026
collaborators

43 papers

cs.LG2026

Sharding Prevents LLM Oversight Failures and Adversarial Exploitation

Victor Akinwande, J. Zico Kolter, Aran Nayebi

Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts, some decisions become weakly grounded in the evidenc…

cs.CL2026

Compressed Sensing for Capability Localization in Large Language Models

Anna Bair, Yixuan Even Xu, Mingjie Sun +1

Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We show that Transformer architectur…

cs.CR2026

A New Framework for Cybersecurity Refusals in AI Agents

Eliot Krzysztof Jones, Mateusz Dziemian, Matt Fredrikson +1

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existin…

cs.LG2026

ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use

Jeremy Tien, Abishek Anand, Yu-Rou Tuan +3

As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerations surrounding t…

cs.LG2026

Reevaluating Policy Gradient Methods for Imperfect-Information Games

Max Rudolph, Nathan Lichtle, Sobhan Mohammadpour +6

In the past decade, motivated by the putative failure of naive self-play deep reinforcement learning (DRL) in adversarial imperfect-information games, researchers have developed nu…

cs.AI2026

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

Jingchu Gai, Guanning Zeng, Christina Baek +4

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving rea…