Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Paper • 2609.38143 • Published • 85
Xiaocheng Yang
Xiaocheng-Yang
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI upvoted a paper about 1 month ago
Cliff: Learning Process Rewards from the First Mistake upvoted a paper about 2 months ago
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via HarnessesOrganizations
None yet
upvoted a paper 10 days ago
upvoted a paper about 1 month ago
upvoted 2
papers about 2 months ago
upvoted 3
papers 3 months ago
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
Paper • 2607.17250 • Published • 93
Trimming the Long-Tail of Visual World Modeling Evaluation
Paper • 2606.24256 • Published • 41
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Paper • 2606.28187 • Published • 14
upvoted 3
papers 4 months ago
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Paper • 2606.22388 • Published • 96
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
Paper • 2606.05622 • Published • 45
Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues
Paper • 2606.02754 • Published • 13
upvoted 2
papers 5 months ago
upvoted 4
papers over 1 year ago
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
Paper • 2505.24846 • Published • 15
Time-R1: Towards Comprehensive Temporal Reasoning in LLMs
Paper • 2505.13508 • Published • 16
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
Paper • 2505.02391 • Published • 25
RM-R1: Reward Modeling as Reasoning
Paper • 2505.02387 • Published • 81