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

When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-time paradigms, namely Direct, CoT, ReAct, Plan-Execute,…

Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision…

Classical sampling-based motion planners like the RRTs suffer from inefficiencies, particularly in cluttered or high-dimensional spaces, due to their reliance on undirected, random sampling. This paper introduces the Episodic RRT, a novel…

In this paper, we introduce Auto-Intent, a method to adapt a pre-trained large language model (LLM) as an agent for a target domain without direct fine-tuning, where we empirically focus on web navigation tasks. Our approach first discovers…

Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward…

As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed…

Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with Large Language Model (LLM)-powered agents, but existing…

Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical…

Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reasoning attainable in a…

As learning-based robotic controllers are typically trained offline and deployed with fixed parameters, their ability to cope with unforeseen changes during operation is limited. Biologically inspired, this work presents a framework for…

Large language models excel at many tasks but often incur high inference costs during deployment. To mitigate hallucination, many systems use a knowledge graph to enhance retrieval-augmented generation (KG-RAG). However, the large amount of…

Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable…

Effective e-commerce risk management requires in-depth case investigations to identify emerging fraud patterns in highly adversarial environments. However, manual investigation typically requires analyzing the associations and couplings…

Evaluating LLM agent trajectories is fundamentally task-specific: a code-debugging agent should be judged on Correctness and Error Handling, not on Fluency or Safety. Yet the dominant paradigm -- LLM-as-Judge with a fixed rubric -- applies…

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…

Autonomous multi-agent systems such as hospital robots and package delivery drones often operate in highly uncertain environments and are expected to achieve complex temporal task objectives while ensuring safety. While learning-based…

Recent advancements in deep-learning-based driving planners have primarily focused on elaborate network engineering, yielding limited improvements. This paper diverges from conventional approaches by exploring three fundamental yet…

This study investigates router-based multi-agent systems for automating foundation design calculations through intelligent task classification and expert selection. Three approaches were evaluated: single-agent processing, multi-agent…

2026 has brought an explosion of interest in LLM-guided evolution of agentic artifacts, with systems like GEPA and Autoresearch demonstrating that LLMs can iteratively improve prompts, code, and agent architectures across diverse domains.…

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…