Related papers: Refining Manually-Designed Symbol Grounding and Hi…

Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and…

The analysis of industrial processes, modelled as descriptor systems, is often computationally hard due to the presence of both algebraic couplings and difference equations of high order. In this paper, we introduce a control refinement…

Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances,…

Reward design is a fundamental, yet challenging aspect of reinforcement learning (RL). Researchers typically utilize feedback signals from the environment to handcraft a reward function, but this process is not always effective due to the…

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…

As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are…

Despite their powerful text generation capabilities, large language models (LLMs) still struggle to effectively utilize external tools to solve complex tasks, a challenge known as tool learning. Existing methods primarily rely on supervised…

For robotic vehicles to navigate robustly and safely in unseen environments, it is crucial to decide the most suitable navigation policy. However, most existing deep reinforcement learning based navigation policies are trained with a…

Refinement is a powerful mechanism for mastering the complexities that arise when formally modelling systems. Refinement also brings with it additional proof obligations -- requiring a developer to discover properties relating to their…

Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. While these improve performance, they often reach a saturation point.…

Existing policy-gradient methods for auto-regressive language models typically select subsequent tokens one at a time as actions in the policy. While effective for many generation tasks, such an approach may not fully capture the structure…

Designing mechanical linkages involves combinatorial topology selection and continuous parameter fitting. We show that language models can systematically improve linkage designs through symbolic representations. Language model agents…

An important problem in geometric reasoning is to find the configuration of a collection of geometric bodies so as to satisfy a set of given constraints. Recently, it has been suggested that this problem can be solved efficiently by…

Finite element discretizations of problems in computational physics often rely on adaptive mesh refinement (AMR) to preferentially resolve regions containing important features during simulation. However, these spatial refinement strategies…

Providing explanations is considered an imperative ability for an AI agent in a human-robot teaming framework. The right explanation provides the rationale behind an AI agent's decision-making. However, to maintain the human teammate's…

Large language models (LLMs) have shown strong performance in many reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one of the leading causes for such performance. LLMs, in fact, are…

Advancements in deep learning have significantly improved model performance across tasks involving code, text, and image processing. However, these models still exhibit notable mispredictions in real-world applications, even when trained on…

Recent studies show that Large Language Models (LLMs) achieve strong reasoning capabilities through supervised fine-tuning or reinforcement learning. However, a key approach, the Process Reward Model (PRM), suffers from reward hacking,…

A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions…

Hyperparameter selection generally relies on running multiple full training trials, with selection based on validation set performance. We propose a gradient-based approach for locally adjusting hyperparameters during training of the model.…