5 papers
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
Jack Hopkins, Dipika Khullar, Fabien Roger
Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information. To better elicit hidden information…
Self-Attribution Bias: When AI Monitors Go Easy on Themselves
Dipika Khullar, Jack Hopkins, Rowan Wang +1
Agentic systems increasingly rely on language models to monitor their own behavior. For example, coding agents may self critique generated code for pull request approval or assess…
Co-Evolving Agents: Learning from Failures as Hard Negatives
Yeonsung Jung, Trilok Padhi, Sina Shaham +4
Self-evolving agents improve their performance on long-horizon tasks by learning from their own interactions with an environment. A common approach uses the resulting failed trajec…
Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning
Chan Young Park, Jillian Fisher, Marius Memmel +4
Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic exe…
Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
Israfel Salazar, Manuel Fernández Burda, Shayekh Bin Islam +42
The evaluation of vision-language models (VLMs) has mainly relied on English-language benchmarks, leaving significant gaps in both multilingual and multicultural coverage. While mu…