Related papers: SkillGrad: Optimizing Agent Skills Like Gradient D…

Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting…

Prior work introduced a gradient descent trained expert system that conceptually combines the learning capabilities of neural networks with the understandability and defensible logic of an expert system. This system was shown to be able to…

As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

We consider the problem of scheduling in constrained queueing networks with a view to minimizing packet delay. Modern communication systems are becoming increasingly complex, and are required to handle multiple types of traffic with widely…

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and…

Many economic games and machine learning approaches can be cast as competitive optimization problems where multiple agents are minimizing their respective objective function, which depends on all agents' actions. While gradient descent is a…

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

Discovering scaling laws for predicting model performance at scale is a fundamental and open-ended challenge, mostly reliant on slow, case specific human experimentation. To investigate the potential for LLMs to automate this process, we…

There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model changes. However, for…

Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control…

We introduce a new Swarm-Based Gradient Descent (SBGD) method for non-convex optimization. The swarm consists of agents, each is identified with a position, ${\mathbf x}$, and mass, $m$. The key to their dynamics is communication: masses…

Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) are considered a promising foundation to build such agents…

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee efficient task…

Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse…

Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a reinforcement learning-augmented LLM agent framework that…

We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently exploring the full parameter space during training. This strategy…

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…