Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning
Clinical decision-making requires nuanced reasoning over heterogeneous evidence and traceable justifications. While recent LLM multi-agent systems (MAS) show promise, they largely optimise …
Tensor Factorization for Temporal Knowledge Graph Forecasting
Tensor factorization has long been a cornerstone of knowledge graph (KG) reasoning, achieving state-of-the-art performance on static link prediction tasks with models …
Agentic Uncertainty Reveals Agentic Overconfidence
Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, …
Same Answer, Different Representations: Hidden Instability in VLMs
The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. …
Interference-Aware Composition of Steering Vectors
Steering vectors are a flexible mechanism for controlling large language models (LLMs) along interpretable behaviours. Multi-behaviour steering, however, remains challenging due to …
Enhancing Long Document Long Form Summarisation with Self-Planning
We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the …
Low-Rank Compression of Language Models via Differentiable Rank Selection
Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves …
GRADA: Graph-based Reranker against Adversarial Documents Attack
Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved …
OpenSIR: Open-Ended Self-Improving Reasoner
Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' …