Pinned Loading

1. JetBrains-Research/the-complexity-trap JetBrains-Research/the-complexity-trap Public

   This repo accompanies the paper "The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management" presented at the Fourth Deep Learning for Code (D…

   Python 7 2

2. JetBrains-Research/git-good-bench JetBrains-Research/git-good-bench Public

   Repository accompanying our REALM '25 publication: "GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git"

   Jupyter Notebook 4 1

3. ctim-rover ctim-rover Public

   Code accompanying the REALM '25 publication: "From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents"

   Jupyter Notebook 2

4. multlingual-lexical-simplification multlingual-lexical-simplification Public

   Team project in the NLP Lab at TU Munich in the Summer Semester 2024. Built an open-source, plug-and-play benchmark suite for lexical simplification. Investigated multilingual transfer learning and…

   Jupyter Notebook 2 1

5. ARPacman ARPacman Public

   Team project for the course IN2018 Erweiterte Realität in the summer semester 2022 at Technical University Munich

   C

6. RouteLLM RouteLLM Public

   A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

   Python