Related papers: Springdrift: An Auditable Persistent Runtime for L…
Agentic applications are LLMs that iteratively invoke external tools to accomplish complex tasks. Such tool-based agents are rapidly becoming the dominant paradigm for deploying language models in production. Unlike traditional single-turn…
Longitudinal health agents must reason across multi-source trajectories that combine continuous device streams, sparse clinical exams, and episodic life events - yet evaluating them is hard: real-world data cannot be released at scale, and…
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…
Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the…
Long-running LLM agents require persistent memory to preserve state across interactions, yet most deployed systems manage memory with age-based retention (e.g., TTL). While TTL bounds item lifetime, it does not bound the computational…
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…
Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critical systems demands more than predictive accuracy. Standard…
Autonomous agent systems are governed by enforcement mechanisms that flag hard constraint violations at runtime. The Agent Control Protocol identifies a structural limit of such systems: a correctly-functioning enforcement engine can enter…
LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…
The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…
As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and…
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…
AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these…
Persistent memory is turning language-model-based agents from stateless participants in isolated interactions into state-bearing components of LLM-based multi-agent systems. As memory becomes durable, reloadable, and behavior-shaping across…
Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human input requirements and limited ability to adapt over time.…
LLM-based foundation agents that perceive, reason, and act across thousands of reasoning steps are rapidly becoming the dominant paradigm for deploying artificial intelligence in open-ended, long-horizon complex tasks. Despite this…
Runtime verification enables checking temporal logic specifications over individual execution traces and offers a scalable alternative to exhaustive formal verification. In practice, systems must satisfy dozens to hundreds of temporal…
Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why…
While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…
As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…