Meta Context Engineering via Agentic Skill Evolution
Paper • 2601.21557 • Published • 2
Jay
JayXDev
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
Meta Context Engineering via Agentic Skill Evolution upvoted a paper about 11 hours ago
Bayesian Model Merging upvoted a paper about 11 hours ago
Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-ExpertsOrganizations
None yet
upvoted 20
papers about 11 hours ago
Bayesian Model Merging
Paper • 2605.12843 • Published • 2
Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts
Paper • 2602.03473 • Published • 11
From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
Paper • 2510.07624 • Published • 9
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
Paper • 2605.09932 • Published • 2
Instance-Aware Parameter Configuration in Bilevel Late Acceptance Hill Climbing for the Electric Capacitated Vehicle Routing Problem
Paper • 2605.00572 • Published • 1
A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization
Paper • 2605.09094 • Published • 1
Bilevel Autoresearch: Meta-Autoresearching Itself
Paper • 2603.23420 • Published • 2
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
Paper • 2403.03542 • Published • 1
Scorio.jl: A Julia package for ranking stochastic responses
Paper • 2603.14103 • Published • 1
Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver
Paper • 2604.25067 • Published • 2
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents
Paper • 2407.16741 • Published • 89
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
Paper • 2609.25001 • Published • 113
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 101
AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets
Paper • 2512.10971 • Published • 13
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 264
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Paper • 2609.23986 • Published • 14
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 56
Atria Dawn: The Dawn of Agentic Superintelligence
Paper • 2609.15818 • Published • 423
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 152