Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges
Paper ā¢ 2610.35193 ā¢ Published ā¢ 27
AI & ML interests
None defined yet.
Recent Activity
Papers
What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
Learning to Retrieve from Agent Trajectories
JeryiĀ
authored a
paper 3 days ago
JeryiĀ
authored a
paper 18 days ago
JeryiĀ
submitted a
paper to Daily Papers 22 days ago
JeryiĀ
authored 3
papers 2 months ago
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Paper ā¢ 2608.25593 ā¢ Published ā¢ 85
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
Paper ā¢ 2608.04436 ā¢ Published ā¢ 63
NeuroCogMap Reveals Cognitive Organization of Large Language Models
Paper ā¢ 2607.00397 ā¢ Published ā¢ 8
JeryiĀ
submitted a
paper to Daily Papers 4 months ago
JeryiĀ
authored a
paper 8 months ago
JeryiĀ
submitted a
paper to Daily Papers 8 months ago
JeryiĀ
updated a
Space 8 months ago
JeryiĀ
published a
Space 8 months ago
JeryiĀ
authored a
paper 9 months ago
JeryiĀ
submitted 2
papers to Daily Papers 9 months ago
JeryiĀ
authored 4
papers 9 months ago
CreAgent: Towards Long-Term Evaluation of Recommender System under Platform-Creator Information Asymmetry
Paper ā¢ 2502.07307 ā¢ Published ā¢ 1
Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
Paper ā¢ 2505.12886 ā¢ Published ā¢ 2
Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs
Paper ā¢ 2512.00908 ā¢ Published
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
Paper ā¢ 2601.11000 ā¢ Published ā¢ 27
JeryiĀ
submitted a
paper to Daily Papers 9 months ago
JeryiĀ
authored a
paper 11 months ago