13 citations · 13 across the 10 of their papers we have counts for
10 papers
Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds
Lars Benedikt Kaesberg, Tianyu Yang, Florian Valentin Wunderlich +4
Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet recent work shows that their failures often reflect an interaction between visual grounding and dow…
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
Niklas Bauer, Lars Benedikt Kaesberg, Akiko Aizawa +3
As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safe…
Decision Protocols in Multi-Agent Large Language Model Conversations
Lars Benedikt Kaesberg
Improving the task performance of Large Language Models (LLMs) is essential, yet scaling these models faces significant challenges such as diminishing returns and high costs. Multi…
Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling
Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle +2
Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effect…
Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym
Lars Benedikt Kaesberg, Tianyu Yang, Niklas Bauer +3
Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate models in a one-shot settin…
MALLM: Multi-Agent Large Language Models Framework
Jonas Becker, Lars Benedikt Kaesberg, Niklas Bauer +3
Multi-agent debate (MAD) has demonstrated the ability to augment collective intelligence by scaling test-time compute and leveraging expertise. Current frameworks for multi-agent d…
SPaRC: A Spatial Pathfinding Reasoning Challenge
Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas +1
Existing reasoning datasets saturate and fail to test abstract, multi-step problems, especially pathfinding and complex rule constraint satisfaction. We introduce SPaRC (Spatial Pa…
Stay Focused: Problem Drift in Multi-Agent Debate
Jonas Becker, Lars Benedikt Kaesberg, Andreas Stephan +3
Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks. Howeve…
Voting or Consensus? Decision-Making in Multi-Agent Debate
Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle +2
Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers,…
CiteAssist: A System for Automated Preprint Citation and BibTeX Generation
Lars Benedikt Kaesberg, Terry Ruas, Jan Philip Wahle +1
We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation. Our system extracts metadata, such…