Related papers: FlyRoute: Self-Evolving Agent Profiling via Data F…

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…

A major challenge in autonomous vehicle research is modeling agent behaviors, which has critical applications including constructing realistic and reliable simulations for off-board evaluation and forecasting traffic agents motion for…

General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in continual parameter-efficient tuning (PET) of pretrained models…

Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and updated, while paying less attention to how experience should…

Large language model (LLM) agents at the network edge offer low-latency execution for routine queries. In contrast, complex requests often require the superior capability of cloud models, incurring higher latency and cost. To navigate this…

This paper documents a case study in agent-driven autonomous reinforcement learning research for quadruped locomotion. The setting was not a fully self-starting research system. A human provided high-level directives through an agentic…

Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typically performed under strict cost and latency constraints,…

We study how to endow GUI agents with scalable memory that help generalize across unfamiliar interfaces and long-horizon tasks. Prior GUI agents compress past trajectories into text tokens, which balloons context length and misses decisive…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly…

Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper formalizes the…

Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fundamental challenges. First, the intractable credit…

The rapid development of AI agent systems is leading to an emerging Internet of Agents, where specialized agents operate across local devices, edge nodes, private services, and cloud platforms. Although recent efforts have improved agent…

This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs), aiming for a more accurate assessment of their capabilities and limitations. We utilize a multi-agent system to…

Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g., private databases, global corpora, and APIs) remains a significant challenge. Existing…

Large Language Models (LLMs) have shown tremendous potential as agents, excelling at tasks that require multiple rounds of reasoning and interactions. Rejection Sampling Fine-Tuning (RFT) has emerged as an effective method for finetuning…

Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language…

Large Language Models (LLMs) and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the…

As robots (edge-devices, agents) find uses in an increasing number of settings and edge-cloud resources become pervasive, wireless networks will often be shared by flows of data traffic that result from communication between agents and…

LLM agents are widely deployed in complex interactive tasks, yet privacy constraints often preclude centralized optimization and co-evolution across dynamic environments. Despite the demonstrated success of Federated Learning (FL) on static…