Related papers: SkillFlow: Efficient Skill and Code Transfer Through Communication in Adapting AI Agents

Related papers

FrogNano: Training a 4B Coding Agent via Online Task Synthesis [61.25325155871018]
FrogNano is a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively.<n>It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks.
arXiv Detail & Related papers (2026-09-07T19:39:38Z)
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents [15.598856888948093]
We present textscOpenSkillEval, an automatic evaluation framework for both skill-augmented agent systems and the skills themselves.<n>Instead of relying on static benchmarks, textscOpenSkillEval automatically constructs realistic task instances from evolving real-world artifacts.<n>Using more than 600 dynamically generated task instances and 30 open-source skills, we conduct a systematic evaluation of state-of-the-art models and agent frameworks.
arXiv Detail & Related papers (2026-05-22T14:09:41Z)
Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering [50.72456732323037]
We propose textbfSwarm Skills, a portable specification that extends the Anthropic Skills standard with multi-agent semantics.<n>Swarm Skills turns multi-agent into first-class, distributable assets that consist of roles, execution bounds, and a built-in semantic structure for self-evolution.<n>We show how Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in.
arXiv Detail & Related papers (2026-05-11T06:26:58Z)
SkillNet: Create, Evaluate, and Connect AI Skills [159.47504178122156]
SkillNet is an open infrastructure designed to create, evaluate, and organize AI skills at scale.<n>Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit.
arXiv Detail & Related papers (2026-02-26T14:24:02Z)
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents [6.356997609995175]
Agentic systems increasingly rely on reusable procedural capabilities, textita.k.a., agentic skills, to execute long-horizon reliably.<n>This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update)<n>We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution.
arXiv Detail & Related papers (2026-02-24T13:11:38Z)
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward [5.124116559484265]
The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice.<n>Rather than encoding all procedural knowledge within model weights, agent skills enable dynamic capability extension without retraining.<n>This survey provides a comprehensive treatment of the agent skills landscape, as it has rapidly evolved during the last few months.
arXiv Detail & Related papers (2026-02-12T21:33:25Z)
Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
arXiv Detail & Related papers (2026-02-10T23:06:02Z)
A Cloud-based Multi-Agentic Workflow for Science [0.12314765641075438]
Large Language Models (LLMs) become ubiquitous across various scientific domains.<n>Their lack of ability to perform complex tasks like running simulations or to make complex decisions limits their utility.<n>We present a domain-agnostic, model-independent workflow for an agentic framework that can act as a scientific assistant while being run entirely on cloud.
arXiv Detail & Related papers (2026-01-18T22:37:09Z)
MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era [74.42509044145417]
MegaFlow is a large-scale distributed orchestration system that enables efficient scheduling, resource allocation, and fine-grained task management for agent-environment workloads.<n>In our agent training deployments, MegaFlow successfully orchestrates tens of thousands of concurrent agent tasks while maintaining high system stability and achieving efficient resource utilization.
arXiv Detail & Related papers (2026-01-12T13:25:33Z)
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent [80.83250816918861]
Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought.<n>However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations.<n>We present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision.
arXiv Detail & Related papers (2025-12-23T19:57:49Z)
Idempotent Equilibrium Analysis of Hybrid Workflow Allocation: A Mathematical Schema for Future Work [0.0]
Large-scale AI systems are reshaping how work is divided between people and machines.<n>We formalise this reallocation as an iterated task-delegation map and show that the process converges to a stable idempotent equilibrium.<n>We argue that policies which promote "centaur" human-AI teaming can steer the economy toward the welfare-maximising fixed point.
arXiv Detail & Related papers (2025-08-02T11:28:34Z)
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training [67.895981259683]
General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence.<n>Current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools.<n>We present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework.
arXiv Detail & Related papers (2025-08-01T08:11:31Z)
FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning [57.4737157531239]
Transfer Learning offers the potential to accelerate learning by transferring knowledge across tasks.<n>It faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source policies.<n>In this work we challenge the key issues in TL to improve knowledge transfer, agents performance across tasks and reduce computational costs.
arXiv Detail & Related papers (2025-07-27T22:21:53Z)
Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities [117.49715661395294]
Data structurization can play a promising role by transforming intricate and disorganized data into well-structured forms.<n>This survey presents a first systematic review of how graphs can empower AI agents.
arXiv Detail & Related papers (2025-06-22T12:59:12Z)
Agentic Knowledgeable Self-awareness [79.25908923383776]
KnowSelf is a data-centric approach that applies agents with knowledgeable self-awareness like humans.<n>Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge.
arXiv Detail & Related papers (2025-04-04T16:03:38Z)
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks [52.46737975742287]
We build a self-contained environment with data that mimics a small software company environment.<n>We find that with the most competitive agent, 24% of the tasks can be completed autonomously.<n>This paints a nuanced picture on task automation with LM agents.
arXiv Detail & Related papers (2024-12-18T18:55:40Z)
To Train or Not to Train: Balancing Efficiency and Training Cost in Deep Reinforcement Learning for Mobile Edge Computing [15.079887992932692]
We present a new algorithm to dynamically select when to train a Deep Reinforcement Learning (DRL) agent that allocates resources. Our method is highly general, as it can be directly applied to any scenario involving a training overhead.
arXiv Detail & Related papers (2024-11-11T16:02:12Z)
Latent-Predictive Empowerment: Measuring Empowerment without a Simulator [56.53777237504011]
We present Latent-Predictive Empowerment (LPE), an algorithm that can compute empowerment in a more practical manner. LPE learns large skillsets by maximizing an objective that is a principled replacement for the mutual information between skills and states.
arXiv Detail & Related papers (2024-10-15T00:41:18Z)
SHIRE: Enhancing Sample Efficiency using Human Intuition in REinforcement Learning [11.304750795377657]
We propose SHIRE, a framework for encoding human intuition using Probabilistic Graphical Models (PGMs)<n>SHIRE achieves 25-78% sample efficiency gains across the environments we evaluate at negligible overhead cost.
arXiv Detail & Related papers (2024-09-16T04:46:22Z)
Game On: Towards Language Models as RL Experimenters [8.131696370980379]
We propose an agent architecture that automates parts of the common reinforcement learning experiment workflow. We use a standard Gemini model, without additional fine-tuning, to provide a curriculum of skills to a language-conditioned Actor-Critic algorithm. Additional examination of the ability of the system to build a growing library of skills, and to judge the progress of the training of those skills, also shows promising results.
arXiv Detail & Related papers (2024-09-05T10:38:16Z)
Multi-Agent Reinforcement Learning for Long-Term Network Resource Allocation through Auction: a V2X Application [7.326507804995567]
We formulate offloading of computational tasks from a dynamic group of mobile agents (e.g., cars) as decentralized decision making among autonomous agents. We design an interaction mechanism that incentivizes such agents to align private and system goals by balancing between competition and cooperation. We propose a novel multi-agent online learning algorithm that learns with partial, delayed and noisy state information.
arXiv Detail & Related papers (2022-07-29T10:29:06Z)
Online Learning of Competitive Equilibria in Exchange Economies [94.24357018178867]
In economics, the sharing of scarce resources among multiple rational agents is a classical problem. We propose an online learning mechanism to learn agent preferences. We demonstrate the effectiveness of this mechanism through numerical simulations.
arXiv Detail & Related papers (2021-06-11T21:32:17Z)
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning [102.36450942613091]
We propose an inverse reinforcement learning algorithm, called emphinverse temporal difference learning (ITD) We show how to seamlessly integrate ITD with learning from online environment interactions, arriving at a novel algorithm for reinforcement learning with demonstrations, called $Psi Phi$-learning.
arXiv Detail & Related papers (2021-02-24T21:12:09Z)
Latent Skill Planning for Exploration and Transfer [49.25525932162891]
In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent. We leverage the idea of partial amortization for fast adaptation at test time. We demonstrate the benefits of our design decisions across a suite of challenging locomotion tasks.
arXiv Detail & Related papers (2020-11-27T18:40:03Z)
Deep active inference agents using Monte-Carlo methods [3.8233569758620054]
We present a neural architecture for building deep active inference agents in continuous state-spaces using Monte-Carlo sampling. Our approach enables agents to learn environmental dynamics efficiently, while maintaining task performance. Results show that deep active inference provides a flexible framework to develop biologically-inspired intelligent agents.
arXiv Detail & Related papers (2020-06-07T15:10:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.