相关论文: Achieving Fairness in DareFightingICE Agents Evalu…

Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However,…

We introduce a unified mathematical and probabilistic framework for understanding and comparing diverse AI agent strategies. We bridge the gap between high-level agent design concepts, such as ReAct, multi-agent systems, and control flows,…

As Retrieval-Augmented Generation (RAG) systems evolve toward more sophisticated architectures, ensuring their trustworthiness through explainable and robust evaluation becomes critical. Existing scalar metrics suffer from limited…

With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…

Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise. When agents share a common reward, each agent's learning signal is computed from a shared return that depends on all agents, so the…

The ability to use tools is fundamental for large language model (LLM) agents. Given a task, existing systems use LLMs to plan and generate tool calls, which are executed by real-world tools to complete the task. However, tool calls are…

In recent years, advances in deep learning have resulted in a plethora of successes in the use of reinforcement learning (RL) to solve complex sequential decision tasks with high-dimensional inputs. However, existing systems lack the…

Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps…

In this work a general framework is proposed to support the development of software systems that are able to adapt their behaviour according to the operating environment changes. The proposed approach, named REPTILE, works in a complete…

High Performance Computing (HPC) systems are used across a wide range of disciplines for both large and complex computations. HPC systems often receive many thousands of computational tasks at a time, colloquially referred to as jobs. These…

The recent years witness a trend of applying large-scale distributed deep learning in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality. The HPC community feels a…

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment expectations and post-deployment outcomes. We review controlled…

Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black…

In public transport networks disruptions may occur and lead to travel delays. It is thus interesting to determine whether a traveler can be resilient to delays that occur unexpectedly, ensuring that they can reach their destination in time…

The concurrency control algorithms in transactional systems limits concurrency to provide strong semantics, which leads to poor performance under high contention. As a consequence, many transactional systems eschew strong semantics to…

Yahtzee is a classic dice game with a stochastic, combinatorial structure and delayed rewards, making it an interesting mid-scale RL benchmark. While an optimal policy for solitaire Yahtzee can be computed using dynamic programming methods,…

Job-scheduling games have traditionally assumed fixed processing times. However, in many realistic environments, ranging from cyber-security response to high-frequency trading, a task's duration depends on its starting time. We study…

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation…

In this paper, we address the average consensus problem of multi-agent systems for possibly unbalanced and delay-prone networks with directional information flow. We propose a linear distributed algorithm (referred to as RPPAC) that handles…