Related papers: Answer Only as Precisely as Justified: Calibrated …

Conformal prediction is a learning framework controlling prediction coverage of prediction sets, which can be built on any learning algorithm for point prediction. This work proposes a learning framework named conformal loss-controlling…

Approximations during program analysis are a necessary evil, as they ensure essential properties, such as soundness and termination of the analysis, but they also imply not always producing useful results. Automatic techniques have been…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task…

Collective Adaptive Systems (CAS) consist of a large number of spatially distributed heterogeneous entities with decentralised control and varying degrees of complex autonomous behaviour that may be competing for shared resources even when…

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing…

Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching…

High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These…

Accurate uncertainty quantification is critical for reliable predictive modeling. Existing methods typically address either aleatoric uncertainty due to measurement noise or epistemic uncertainty resulting from limited data, but not both in…

Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks. The underlying coarse action space discretizations often yield favourable exploration…

Just-In-Time (JIT) defect prediction aims to automatically predict whether a commit is defective or not, and has been widely studied in recent years. In general, most studies can be classified into two categories: 1) simple models using…

Rigorous uncertainty quantification is essential for the safe deployment of autonomous systems in unconstrained environments. Conformal Prediction (CP) provides a distribution-free framework for this task, yet its standard formulations rely…

To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods…

Argument Mining (AM) is a foundational technology for automated writing evaluation, yet traditional supervised approaches rely heavily on expensive, domain-specific fine-tuning. While Large Language Models (LLMs) offer a training-free…

Coarsened exact matching (CEM) is often promoted as a superior alternative to propensity score matching (PSM) for addressing imbalance, model dependence, bias, and efficiency. However, this recommendation remains uncertain. First, CEM is…

Autoregressive Predictive Coding (APC), as a self-supervised objective, has enjoyed success in learning representations from large amounts of unlabeled data, and the learned representations are rich for many downstream tasks. However, the…

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their…

Foundation models face growing compute and memory bottlenecks, hindering deployment on resource-limited platforms. While compression techniques such as pruning and quantization are widely used, most rely on uniform heuristics that ignore…

We propose Conformal Lie-group Action Prediction Sets (CLAPS), a symmetry-aware conformal prediction-based algorithm that constructs, for a given action, a set guaranteed to contain the resulting system configuration at a user-defined…

Agentic Retrieval-Augmented Generation (RAG) systems combine iterative search, planning prompts, and retrieval backends, but deployed settings impose explicit budgets on tool calls and completion tokens. We present a controlled measurement…