Volker Tresp

Knowledge graph memory can achieve superior factual recall without the token costs of traditional retrieval methods, but its effectiveness hinges on overcoming the challenge of adapter selection.

Matched execution scores can hide up to 64.3 points of command-path failure, revealing a critical gap in evaluating LLM coding agents.

Self-improving coding agents can achieve unprecedented efficiency and generalizability by learning from multiple task trajectories simultaneously.

Modality Balance can be harnessed as a powerful form of privileged information, leading to substantial gains in reasoning performance for multimodal models.

MADA-RL boosts compact model reasoning accuracy by 2% with 16 times fewer trainable parameters, redefining how critics learn from generators.