Related papers: ElephantBroker: A Knowledge-Grounded Cognitive Run…
The rapid deployment of large language model (LLM)-based agents introduces a new class of risks, driven by their capacity for autonomous planning, multi-step tool integration, and emergent interactions. It raises some risk factors for…
Effective human-AI collaboration on complex reasoning tasks requires that users understand and interact with the model's process, not just receive an output. However, the monolithic text from methods like Chain-of-Thought (CoT) prevents…
As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented…
We present Cogniscope, an open evaluation framework for studying longitudinal early-risk AI systems under controlled behavioral drift, sparse observations, delayed evidence, and heterogeneous progression patterns. Cogniscope combines two…
Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that…
As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…
Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises from LLMs' working memory constraints, which result in their…
The pursuit of autonomous agents capable of temporally coherent planning is hindered by a fundamental flaw in current vision-language models (VLMs): they lack cognitive inertia. Operating on isolated snapshots, these models cannot form a…
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent,…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these…
Operating Elasticsearch clusters at scale demands continuous human expertise spanning the full lifecycle -- from initial deployment through performance tuning, monitoring, failure prediction, and incident recovery. We present the ES…
The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor weaknesses that account for the bulk of security incidents. To tackle these issues, we…
Autonomous agents based on Large Language Models (LLMs) that devise plans and tackle real-world challenges have gained prominence.However, tailoring these agents for specialized domains like quantitative investment remains a formidable…
Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool…
Despite rapid progress in large language model (LLM)-based multi-agent systems, current benchmarks fall short in evaluating their scalability, robustness, and coordination capabilities in complex, dynamic, real-world tasks. Existing…
Autonomous LLM-based agents have emerged as a powerful paradigm for complex task execution, yet the field lacks standardized tools for development, deployment, distribution and discovery of agents. We present Cerebrum, an Agent SDK for AIOS…
Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and…
The Animal-AI Environment is a unique game-based research platform designed to facilitate collaboration between the artificial intelligence and comparative cognition research communities. In this paper, we present the latest version of the…
As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…