Research
A New Study from Harvard and Perplexity Finds AI Agents Perform 26 Minutes of Autonomous Work per Session vs 33 Seconds for Search
Research comparing AI agents to traditional search shows agents can sustain autonomous work for significantly longer periods. The study suggests AI agents may be approaching practical utility for extended task completion, though questions remain about reliability and accuracy over these longer sessions.
Read full story at MarkTechPost →V:0.2 · A:0.4 · D:0.5
Related
Research
Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
Researchers introduce Pythagoras-Prover, a compute-efficient family of Lean theorem provers that achieves strong perform...
Research
Can AI Agents Synthesize Scientific Conclusions?
Researchers created SciConBench, a benchmark testing AI agents' ability to synthesize scientific conclusions from multip...
Research
How memory tools can make AI models worse
New research suggests that AI memory systems intended to improve model performance can actually degrade capabilities and...