language model agents
7 notes, newest first.
Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
Researchers studied how large language model (LLM) agents can learn and apply skills from completed tasks to perform better on future tasks. They found that inducing skills at the subtask level instead of at the task…
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
Researchers introduce Convergent Detour Hijacking (CDH), an attack that manipulates language model (LLM) agents by exploiting their reliance on third-party skills for task selection and planning. The attack can lead to…
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Researchers propose a framework called Safety Harness Evolution (SHE) for improving the safety of large language model agents. SHE focuses on evolving the harness, which manages context, memory, tools, permissions, and…
Self-Evolving World Models for LLM Agent Planning
In this paper, the authors introduce WorldEvolver, a framework for self-evolving world models designed to improve the planning abilities of long-horizon language model agents by offering predictions of action…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
The paper introduces a new method called Joint Learning of Experiential Rules and Policies (JERP) for large language model agents operating in multi-step interactive environments. The main challenge addressed is…
Where Do CoT Training Gains Land in LLM based Agents?
The research investigates the role of Chain-of-Thought (CoT) reasoning in language model agents, finding that while CoT training improves the quality of actions predicted by the model, it does not significantly widen…
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Researchers propose Semantic Consistency Policy Optimization (SCPO), a method to optimize reinforcement learning for Language Model (LLM) agents. SCPO aims to reduce semantic credit inconsistencies that occur when…
