Goto

Collaborating Authors

 Finney County


Maestro: Joint Graph & Config Optimization for Reliable AI Agents

Wang, Wenxiao, Kattakinda, Priyatham, Feizi, Soheil

arXiv.org Artificial Intelligence

Building reliable LLM agents requires decisions at two levels: the graph (which modules exist and how information flows) and the configuration of each node (models, prompts, tools, control knobs). Most existing optimizers tune configurations while holding the graph fixed, leaving structural failure modes unaddressed. We introduce Maestro, a framework-agnostic holistic optimizer for LLM agents that jointly searches over graphs and configurations to maximize agent quality, subject to explicit rollout/token budgets. Beyond numeric metrics, Maestro leverages reflective textual feedback from traces to prioritize edits, improving sample efficiency and targeting specific failure modes. On the IFBench and HotpotQA benchmarks, Maestro consistently surpasses leading prompt optimizers--MIPROv2, GEPA, and GEPA+Merge--by an average of 12%, 4.9%, and 4.86%, respectively; even when restricted to prompt-only optimization, it still leads by 9.65%, 2.37%, and 2.41%. Maestro achieves these results with far fewer rollouts than GEPA. We further show large gains on two applications (interviewer & RAG agents), highlighting that joint graph & configuration search addresses structural failure modes that prompt tuning alone cannot fix.


WavePulse: Real-time Content Analytics of Radio Livestreams

Mittal, Govind, Gupta, Sarthak, Wagle, Shruti, Chopra, Chirag, DeMattee, Anthony J, Memon, Nasir, Ahamad, Mustaque, Hegde, Chinmay

arXiv.org Artificial Intelligence

Radio remains a pervasive medium for mass information dissemination, with AM/FM stations reaching more Americans than either smartphone-based social networking or live television. Increasingly, radio broadcasts are also streamed online and accessed over the Internet. We present WavePulse, a framework that records, documents, and analyzes radio content in real-time. While our framework is generally applicable, we showcase the efficacy of WavePulse in a collaborative project with a team of political scientists focusing on the 2024 Presidential Elections. We use WavePulse to monitor livestreams of 396 news radio stations over a period of three months, processing close to 500,000 hours of audio streams. These streams were converted into time-stamped, diarized transcripts and analyzed to track answer key political science questions at both the national and state levels. Our analysis revealed how local issues interacted with national trends, providing insights into information flow. Our results demonstrate WavePulse's efficacy in capturing and analyzing content from radio livestreams sourced from the Web. Code and dataset can be accessed at \url{https://wave-pulse.io}.


Breaking News, World News & Multimedia

#artificialintelligence

Conservatives are girding for an extended clash on two fronts in the months ahead: one with a possible Clinton administration and one with Republicans who rejected Donald J. Trump. Megyn Kelly's divergent approach at Fox News took a different turn in her exchange with Newt Gingrich and again raised the question of the channel's future. A lot of healthy people are defying predictions by the Affordable Care Act architects and refusing to enroll, throwing off the calculations behind the system. The startling double-digital declines in TV viewership raise questions about whether the football and soccer leagues have reached their peak. Mr. Beatty's "Rules Don't Apply" is the first film he has written, directed and starred in since "Bulworth" in 1998.