Continual and self-improving learning
22 notes, newest first. Includes the vault tags continual learning, self-evolving agents.
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
Growing Harness learns the agent harness itself from a strategy-free scaffold. Function-level traces localize failures, an optimizer repairs bounded code surfaces, and a held-out success-first gate rolls back repairs…
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
Designer-RSI uses a frozen frontier model operating professional design software through more than 230 tools and maintains an external procedural-memory bank of natural-language skills. The memory widens by adding…
An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage
The authors propose a lightweight approach to Federated Continual Learning (FCL) called FedCurv-DR for supporting artificial intelligence in cultural heritage. This method is designed to learn from distributed and…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
The paper presents a new paradigm for continual learning called Harness Continual Learning (HCL). In this approach, an agent can adapt through a harness of prompts, memories, tools, skills, and routing rules. The…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
The paper 'Harness Continual Learning: Continual Adaptation Beyond Model Parameters' introduces a new approach to continual learning, focusing on the evolution of an agent's harness (which includes prompts, memories…
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
The paper presents SkillZip, an evaluation-free method for compressing skills used by self-evolving agents. SkillZip aims to make skill compression more efficient by finding the shortest faithful structural explanation…
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
The paper presents SkillZip, an evaluation-free method for compressing skills by finding their shortest faithful structural explanations. It aims to reduce the repetition and expense of injecting and maintaining skills…
Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?
A study compared an open-ended optimization (OEO) method with two prescribed approaches for self-evolving agents. The OEO method uses a frontier model as the optimizer, while the prescribed methods have fixed pipelines…
Continual Learning in Transition
The paper examines the evolution of Continual Learning (CL), a method that allows models to update and retain knowledge while learning new tasks. The authors suggest a transition from traditional parameter-centric…
Continual Learning in Transition
The text discusses a shift in continual learning, moving away from traditional parameter-centric methods towards system-level adaptation. The authors propose a tri-axial framework to analyze this transition: When, How…
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
Researchers have created a new benchmark for self-evolving agents in financial workflows called FinEvo-Bench. The benchmark includes 120 real-life tasks across six domains, with each task having a specific professional…
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
Researchers introduce a new benchmark called FinEvo-Bench for testing self-evolving agents in various financial workflows. The benchmark consists of 120 real-world tasks across six domains, with each task having a…
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
The study introduces FinEvo-Bench, a benchmark for evaluating the performance of self-evolving agents in various financial tasks. The benchmark consists of 120 real-case-grounded tasks across six financial domains…
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
The research evaluates if improvements from agent-optimization methods can stack up over time in a continual learning setting. Three optimizer-driven methods (GEPA, Meta Harness, and RELAI's Verifiable Continual…
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
Researchers investigated if improvements made by agent-optimization methods persist when agents are optimized again on new tasks. They found that one method called RELAI-VCL was the only one that both transferred…
From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
Researchers propose a framework called EvoSOP to help large language model (LLM) agents optimize their toolset by synthesizing atomic actions into reusable Standard Operating Procedures (SOPs). This approach aims to…
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
The researchers explore the impact of biased judges in self-evolving agents, focusing on skill retirement, a mechanism that helps maintain the quality of an agent's knowledge base by retiring poorly performing skills…
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
The research presents ManimAgent, a self-evolving multimodal agent that learns from its failures and successes in generating Python code using the Manim library to render mathematical animations. The agent stores these…
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
The paper presents a new method to create motion-language agents that can understand and generate human movements in dynamic environments without forgetting previously acquired skills. The method, called LoRA variants…
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
Researchers propose a method to create motion-language agents that can understand and generate human movements in dynamic environments without forgetting previously learned skills. They introduce low-rank adaptation…
Can Scale Save Us From Plasticity Loss in Large Language Models?
Researchers studied plasticity loss, a challenge in creating neural networks capable of continuous learning, in modern transformer-based language models (LLMs). They found evidence of plasticity loss across various…
RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
The paper proposes a new approach for training Vision-Language-Action (VLA) models through active, continual learning. This method aims to address the inefficiencies of traditional passive imitation learning by…
