3 papers
cs.CL2026
A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents
A. Sayyad, J. Emmons, S. Jones +2
We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in…
cs.LG2025
LZ Penalty: An information-theoretic repetition penalty for autoregressive language models
Antonio A. Ginart, Naveen Kodali, Jason Lee +3
We introduce the LZ penalty, a penalty specialized for reducing degenerate repetitions in autoregressive language models without loss of capability. The penalty is based on the cod…
cs.AI2024
Asynchronous Tool Usage for Real-Time Agents
Antonio A. Ginart, Naveen Kodali, Jason Lee +3
While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synch…