相关论文: Traversal-as-Policy: Log-Distilled Gated Behavior …

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling,…

The transition of Large Language Models (LLMs) from passive code generators to autonomous agents introduces significant safety risks, specifically regarding destructive commands and inconsistent system states. Existing commercial solutions…

LLM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting. If directive-bearing state is dropped, weakened, or rebound during that step, an agent…

Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on…

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational policy because the facts needed for correct policy judgment are hidden at decision time. We…

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…

Long-horizon planning in realistic environments requires the ability to reason over sequential tasks in high-dimensional state spaces with complex dynamics. Classical motion planning algorithms, such as rapidly-exploring random trees, are…

LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership, and unauthorized reuse difficult to establish from observed…

We introduce Tempest, a multi-turn adversarial framework that models the gradual erosion of Large Language Model (LLM) safety through a tree search perspective. Unlike single-turn jailbreaks that rely on one meticulously engineered prompt,…

The shift toward interacting with frozen, "black-box" Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a critical optimization challenge. We propose a Reinforcement Learning (RL) framework for…

LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance…

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

In the rapidly evolving landscape of software engineering, the demand for robust and secure systems has become increasingly critical. This is especially true for self-adaptive systems due to their complexity and the dynamic environments in…

Recent advancements in reinforcement learning (RL) have led to remarkable achievements in robot locomotion capabilities. However, the complexity and ``black-box'' nature of neural network-based RL policies hinder their interpretability and…

Behavior Trees constitute a widespread AI tool which has been successfully spun out in robotics. Their advantages include simplicity, modularity, and reusability of code. However, Behavior Trees remain a high-level decision making engine;…

Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-stage training pipelines and lack fine-grained,…

Temporal logic can be used to formally specify autonomous agent goals, but synthesizing planners that guarantee goal satisfaction can be computationally prohibitive. This paper shows how to turn goals specified using a subset of finite…

People increasingly use LLM agents for multi-turn financial recommendations, where the agent pulls market data through tools and tracks user preferences across turns. When tool outputs are manipulated, the recommendations stop matching the…