collaborators

7 papers

cs.SE2026

SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks

Seongho Son, Sangwoong Yoon, Jiahua Tang +3

Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier model is wasteful when many iss…

cs.AI2026

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?

Juliusz Ziomek, William Bankes, Lorenz Wolf +3

We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wi…

cs.LG2026

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier

Lorenz Wolf, Connor Watts, Roger Creus Castanyer +4

The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current mod…

cs.CR2026

unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning

Geoffrey Bradway, Roger Creus Castanyer, Lorenz Wolf +3

Unix competence is the ability to use shell and operating-system primitives as first-class tools, not merely to write programs through a terminal. Current terminal benchmarks tend…

cs.AI2026

PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play

Roger Creus Castanyer, Geoffrey Bradway, Lorenz Wolf +3

We introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs. Teachers and students are…

cs.LG2025

Reward Model Overoptimisation in Iterated RLHF

Lorenz Wolf, Robert Kirk, Mirco Musolesi

Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model o…