Leon Engländer

@LeonEnglaender

training code agents @cohere | prev. open-source @AdapterHub (100k+ PyPI installs/mo) | prev. @UKPLab | 🇩🇪→🇨🇦

Joined October 2022

396 Following

443 Followers

Replies Reposts Media

Pinned
Leon Engländer
@LeonEnglaender
Apr 21
LLM agents are assumed to integrate unexpected environmental observations into their reasoning. It turns out they don't. We added the complete task solution into agent environments as a file or an API endpoint, and measured whether agents act on what they discover. They almost
Cohere and 3 others
9
Leon Engländer
@LeonEnglaender
11h
Agents now run experiments end to end. For RSI they must react to nuances that don't fit their implicit world view. This requires environmental curiosity. Surprisingly agents do not show even way simpler forms of environmental curiosity. Thanks @lusxvr for highlighting our work!
Luis
@lusxvr
12h
Paper Spotlight: Do AI agents notice what is right in front of them? If the full solution to a task is injected into the agent's environment, e.g. a solution.sh file in the working folder on Terminal-Bench, -> Agents find it in about 80% of runs -> They use it in only 37-50%
3
Leon Engländer
@LeonEnglaender
Oct 29
Internal progress on code agents has been incredible. Directionally very, very good. And now we have the funding to scale it much further. Very hyped for the next releases 👀
Cohere
@cohere
Oct 29
We're proud to announce the initial close of our Series E, targeting up to CAD $7 billion at a CAD $35.7 billion valuation; marking the largest private financing round in Canadian startup history.
3
Leon Engländer
@LeonEnglaender
Oct 6
I'm at COLM in SF this week! I work on agentic code gen at @cohere. If you want to talk about training code agents, DM me. Our team is also hiring:
jobs.ashbyhq.com
Member of Technical Staff, Agent Code
Help drive the development of cutting-edge code LLMs and agent systems that can interact with the digital world to solve complex tasks with minimal human oversight
10
Leon Engländer
@LeonEnglaender
Jun 9
We're just 8 people on our core code team and our 30B-A3B model lands on par with Claude Haiku 4.5 and ahead of NVIDIA's 120B-A12B Nemotron 3 Super on the Artificial Analysis Coding Index. Released under Apache 2.0. Very proud of our work & lots more to come!
Cohere
@cohere
Jun 9
06:10
Introducing Cohere's first open-source coding model: North Mini Code Small & efficient, designed for agentic performance and built for community input.
19

Leon Engländer

Leon Engländer’s posts