Related papers: AgentCourt: Simulating Court with Adversarial Evol…
With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry. However, most current efforts focus on tasks within individual…
Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to…
Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective…
Software testing is a critical, yet resource-intensive phase of the software development lifecycle. Over the years, various automated tools have been developed to aid in this process. Search-based approaches typically achieve high coverage…
LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and adversarial collaboration. Existing defenses fall into two…
The gap between static benchmarks and the dynamic nature of real-world legal practice poses a key barrier to advancing legal intelligence. To this end, we introduce J1-ENVS, the first interactive and dynamic legal environment tailored for…
Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability,…
Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) are considered a promising foundation to build such agents…
Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes -- ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this,…
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent…
Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…
Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…
We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…
Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first…
Current evaluation methods for large language models (LLMs) primarily rely on static benchmarks, presenting two major challenges: limited knowledge coverage and fixed difficulties that mismatch with the evaluated LLMs. These limitations…
The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches…
Mock trial has long served as an important platform for legal professional training and education. It not only helps students learn about realistic trial procedures, but also provides practical value for case analysis and judgment…
Complex agentic AI systems, powered by a coordinated ensemble of Large Language Models (LLMs), tool and memory modules, have demonstrated remarkable capabilities on intricate, multi-turn tasks. However, this success is shadowed by…
Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…