Related papers: SIA: Self Improving AI with Harness & Weight Updat…
As large language models (LLMs) transition into autonomous agents integrated with extensive tool ecosystems, traditional routing heuristics increasingly succumb to context pollution and "overthinking". We argue that the bottleneck is not a…
What is the best harness for cybersecurity AI? Cybersecurity systems are converging on a single execution scaffold per agent, an iterative shell loop driven by a Large Language Model (LLM). However, scaffolds are not interchangeable, rarely…
Optimizing human-AI interaction requires users to reflect on their own performance critically. Our paper examines whether people using AI to complete tasks can accurately monitor how well they perform. In Study 1, participants (N = 246)…
This paper introduces a self-learning agent that integrates LLaMA 3.2 with a Progressive Neural Network (PNN) for continual learning in conversational AI and code generation. The framework dynamically collects data, fine-tunes tasks with…
While Deep Neural Networks (DNNs) are deriving the major innovations in nearly every field through their powerful automation, we are also witnessing the peril behind automation as a form of bias, such as automated racism, gender bias, and…
Meta-learning empowers artificial intelligence to increase its efficiency by learning how to learn. Unlocking this potential involves overcoming a challenging meta-optimisation problem. We propose an algorithm that tackles this problem by…
AI algorithms are being used with increased frequency in SE research and practice. Such algorithms are usually commissioned and certified using data from outside the SE domain. Can we assume that such algorithms can be used…
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
System Instructions (SIs), or system prompts, are pivotal for guiding Large Language Models (LLMs) but manual crafting is resource-intensive and often suboptimal. Existing automated methods frequently generate non-human-readable "soft…
Legal argumentation is a vital cornerstone of justice, underpinning an adversarial form of law, and extensive research has attempted to augment or undertake legal argumentation via the use of computer-based automation including Artificial…
AI agents are an exciting new research direction, and agent development is driven by benchmarks. Our analysis of current agent benchmarks and evaluation practices reveals several shortcomings that hinder their usefulness in real-world…
While the pace of development of AI has rapidly progressed in recent years, the implementation of safe and effective regulatory frameworks has lagged behind. In particular, the adaptive nature of AI models presents unique challenges to…
Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly teleoperated demonstration data, large-scale deployment of…
High Energy Physics (HEP) experiments like BESIII produce petabyte-scale data. Extracting physics results requires complex workflows (simulation, reconstruction, statistical analysis, etc.) that traditionally take experts months or years.…
As AI systems increasingly make critical decisions, deceptive AI poses a significant challenge to trust and safety. We present Self-Other Overlap (SOO) fine-tuning, a promising approach in AI Safety that could substantially improve our…
This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game. We identify four inference-time levers that shape performance: model selection, policies and guardrails, centralized data sharing,…
The rapid advancement of Artificial Intelligence (AI) has led to unprecedented computational demands, raising significant environmental and ethical concerns. This paper critiques the prevailing reliance on large-scale, static datasets and…
Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening. Current approaches, like offline fine-tuning and standard…
Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effective and reduces the reliance on human supervision in LLMs'…
Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A model that is always overconfident offers no useful signal for deferral. We present a multi-agent framework that combines domain-specific…