EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Paper • 2610.04184 • Published • 20
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
View all Papers
Mercury7353
submitted a
paper to Daily Papers 13 days ago
qingyun-wu
authored 15
papers over 1 year ago
A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence
Paper • 2507.21046 • Published • 87
FLAML: A Fast and Lightweight AutoML Library
Paper • 1911.04706 • Published • 1
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
Paper • 2310.10873 • Published • 1
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
Paper • 2002.09102 • Published
An Empirical Study on Challenging Math Problem Solving with GPT-4
Paper • 2306.01337 • Published • 2
FairAutoML: Embracing Unfairness Mitigation in AutoML
Paper • 2111.06495 • Published • 1
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Paper • 2308.08155 • Published • 11
Training Language Model Agents without Modifying Language Models
Paper • 2402.11359 • Published • 2
StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
Paper • 2403.11322 • Published • 1
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Paper • 2403.04783 • Published • 2
Adaptive In-conversation Team Building for Language Model Agents
Paper • 2405.19425 • Published
LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
Paper • 2406.00231 • Published • 1
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 304
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Paper • 2505.00212 • Published • 9
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 191