Multimodal in-context learning (ICL) is an important capability of multimodal large language models (MLLMs). Its performance is closely tied to the demonstrations it uses, making demonstration retrieval a core problem for ICL. Common methods use fixed scoring methods to retrieve all the demonstrations at once, which ma...
Yanshu Li, Rui-Xiang Tang, Junyi Jessy Li et al.· 0 citations
Computer-use agents need to capture procedural knowledge of how people use software. User telemetry offers a scalable source of this knowledge. However, learning reusable skills from these logs requires addressing three challenges: (1) Goal Underspecification, since logs do not record the goal behind each action; (2) N...
J. Chen, Elias Stengel-Eskin, Yan Chen et al.· 0 citations
While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly require creativity (e.g., story generation) as well as those that require it implicitly, e.g., reinforcement learning (RL). We instead prop...
Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin· 0 citations
FrankenReport, an interface for long-form knowledge-seeking report generation that supports adaptive early exiting per section, is presented, an interface for long-form knowledge-seeking report generation that evaluates intermediate outputs during generation and predicts whether further targeted computation will yield...
Zheng-Ping Jiang, Gonzalo Ramos, Ji-Na Suh et al.· 0 citations
It is found that current LLMs have the potential for cumulative cultural evolution -- previously attested only in humans -- with mixed populations of agents developing capacities that go beyond their lowest common denominator.
Elias Stengel-Eskin, Newton Sander, Carlos Bonetti et al.· 2 citations
An evaluation method is proposed that pinpoints which agent introduced each error by locally testing agent invocations for faithfulness and verifiability relative to their own inputs and proposes a four-type taxonomy to categorize the discovered errors: hallucination, uncited input reliance, uncited output, or insuffic...
Eran Hirsch, David Wan, Han Wang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.