TTSE: A Two-Track Online Self-Evolution Framework
cs.LG, cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 20 pages, 2 figures, 18 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Memp: Exploring Agent Procedural Memory
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
- MemGPT: Towards LLMs as Operating Systems
- $\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
- Cognitive Architectures for Language Agents
- From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents
- MIRIX: Multi-Agent Memory System for LLM-Based Agents
- WebXSkill: Skill Learning for Autonomous Web Agents
- Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses
- GraSP: Graph-Structured Skill Compositions for LLM Agents
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- Reinforcement World Model Learning for LLM-based Agents
- MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
- Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?
- GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks