$au^2$-bench
PulseAugur coverage of $au^2$-bench — every cluster mentioning $au^2$-bench across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New pipeline enables spoken agents to act while listening
Researchers have developed a novel synthetic spoken-dialogue pipeline to address the latency challenges in spoken agents. This pipeline generates dialogues with annotations indicating the earliest point at which a tool …
-
PerMIT architecture secures LLM agent memory with integrity theorems
Researchers have developed PerMIT, a novel memory architecture designed to enhance the security and integrity of persistent memory for Large Language Model (LLM) agents. This system employs machine-checked integrity the…
-
New Signals and Queries method boosts LLM agent efficiency
Researchers have developed a new method called Signals and Queries (S&Q) to improve the efficiency of large language model (LLM) agents. S&Q acts as a preliminary filter, reducing the number of behavioral policies that …
-
SpecAgent protocol halves agent latency and memory use while preserving quality
Researchers have introduced SpecAgent, a new protocol for large language model agents that improves efficiency by having a smaller model draft tool-use steps and a larger model verify them. This approach reduces latency…
-
New research tackles long-horizon decision-making for language agents · 4 sources tracked
Researchers are developing new methods to improve the long-horizon decision-making capabilities of language agents. One approach, RELACE, uses retrospective likelihood scoring to assess actions based on their plausibili…
-
AI agent benchmarks flawed by policy loopholes, study finds
A new research paper published on arXiv explores the issue of policy loopholes in AI agent benchmarks, specifically within the $ au^2$-bench domains. The study found that ambiguity, silence, or contradictions in natural…