Ohav (@ohavba) profile picture
Joined February 2024
Photo by Ohav (@ohavba)Photo by Ohav (@ohavba)Photo by Ohav (@ohavba)Photo by Ohav (@ohavba)
"One bad apple can spoil the bunch 🍎", and that's doubly true for language agents! Our new paper shows how monitoring and intervention can prevent agents from going rogue, boosting performance by up to 20%. We're also releasing a new multi-agent environment πŸ•΅οΈβ€β™‚οΈ
2
7
1
28
4,352
Using our method, we see consistent gains across varying difficulty levels of WhoDunitEnv. We apply our method to GovSim, a recent resource sharing environment and show an increase in both survival rates and efficiency of agents. @giorgiopiatti
1
4
114
We believe monitoring and intervention to be a strong tool when dealing with complex systems. Read more here arxiv.org/abs/2502.05986 @megamor2 @OriYoran
1
6
106
Do you have a "tell" when you are about to lie? We find that LLMs have β€œtells” in their internal representations which allow estimating how knowledgeable a model is about an entity 𝘣𝘦𝘧𝘰𝘳𝘦 it generates even a single token. Paper: arxiv.org/abs/2406.12673v1 🧡 @dhgottesman
2
24
1
115
7,268