Related papers: SkillOpt: Executive Strategy for Self-Evolving Age…
The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new…
Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce…
In reinforcement learning applications like robotics, agents usually need to deal with various input/output features when specified with different state/action spaces by their developers or physical restrictions. This indicates unnecessary…
We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…
With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security…
Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them…
Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement.…
Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly,…
Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…
Automatic Prompt Optimization (APO) has emerged as a critical technique for enhancing Large Language Model (LLM) performance, yet current state-of-the-art methods typically rely on large, labeled gold-standard development sets to compute…
A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using…
Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. Yet, building general-purpose agents by manually embedding foundation models into…
Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and…
It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to…
Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often…
LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting…
AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…
Artifact evaluation has been adopted in the Software Engineering (SE) research community for 15 years, substantially improving research reproducibility across major SE conferences. However, this success has introduced a growing scalability…
The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and…
Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effective technique to align LLMs to human preferences and broader…