Related papers: PAACE: A Plan-Aware Automated Agent Context Engine…

Traditional vehicle routing systems efficiently optimize singular metrics like time or distance, and when considering multiple metrics, they need more processes to optimize . However, they lack the capability to interpret and integrate the…

This paper introduces the Pandemic PACT Advanced Categorisation Engine (PPACE) along with its associated dataset. PPACE is a fine-tuned model developed to automatically classify research abstracts from funded biomedical projects according…

In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale…

Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single session using a 70-billion-parameter model can cost around $127…

LLM-powered agents are emerging as a dominant paradigm for autonomous task solving. Unlike standard inference workloads, agents operate in a strictly serial "LLM-tool" loop, where the LLM must wait for external tool execution at every step.…

Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the quality and reliability of these…

The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures are frequently constructed using imperative, ad hoc patterns.…

Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct…

Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and…

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…

Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS…

Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of…

Large language models (LLMs) have showcased remarkable potential across various tasks by conditioning on prompts. However, the quality of different human-written prompts leads to substantial discrepancies in LLMs' performance, and improving…

Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window, primarily due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). Recent studies…

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce…

Large language models (LLMs) often generate fluent but factually incorrect statements despite having access to relevant evidence, a failure mode rooted in how they allocate attention between contextual and parametric knowledge.…

Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in…

Amortized meta-learning methods based on pre-training have propelled fields like natural language processing and vision. Transformer-based neural processes and their variants are leading models for probabilistic meta-learning with a…