Related papers: SEA-Eval: A Benchmark for Evaluating Self-Evolving…

Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on high-resource languages and fail to evaluate models in…

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…

The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…

Entity alignment (EA) aims to identify entities across different knowledge graphs (KGs) that refer to the same real-world object and plays a critical role in knowledge fusion and integration. Traditional EA methods mainly rely on knowledge…

We propose that AI automation is a continuum between: (i) crashing waves where AI capabilities surge abruptly over small sets of tasks, and (ii) rising tides where the increase in AI capabilities is more continuous and broad-based. We test…

Existing vision-and-language navigation models often deviate from the correct trajectory when executing instructions. However, these models lack effective error correction capability, hindering their recovery from errors. To address this…

Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout…

Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time. Existing…

Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolsets or offline training lags behind these dynamics, leaving…

Pre-trained large language models (LLMs) exhibit powerful capabilities for generating natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and…

In this paper, we propose SEA, a novel approach for active robot exploration through semantic map prediction and a reinforcement learning-based hierarchical exploration policy. Unlike existing learning-based methods that rely on one-step…

Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents…

Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation,…

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…

We present Agent-Diff, a novel benchmarking framework for evaluating agentic Large Language Models (LLMs) on real-world productivity software API tasks via code execution. Agentic LLM performance varies due to differences in models,…

Understanding how the time-complexity of evolutionary algorithms (EAs) depend on their parameter settings and characteristics of fitness landscapes is a fundamental problem in evolutionary computation. Most rigorous results were derived…

Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a significant and promising direction, there still exists many…

LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fixed, human-designed scaffolds that struggle to adapt across diverse targets and failure modes. We introduce \textsc{CyberEvolver}, a…

Large Language Models (LLMs) have emerged as powerful operators for evolutionary search, yet the design of efficient search scaffolds remains ad hoc. While promising, current LLM-in-the-loop systems lack a systematic approach to managing…

As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents…