Tag
AIBuildAI-2.5 introduces an autonomous AI model development system using LLM-guided tree search to enhance efficiency, ranking first on MLE-Bench with a 73.3% medal rate and outperforming baselines on multiple tasks.
ConceptTS introduces an interpretable forecasting framework that uses large language models to propose human-readable concepts for multivariate time-series prediction, achieving competitive accuracy with transparency through concept bottlenecks.
EvoCause is a research paper introducing an LLM-guided approach to refine causal graphs for root cause analysis, using expert diagnostic labels to constrain graph edits and releasing TeleRCA, an expert-annotated alarm benchmark from a production telecom network.
Proposes ULPS, a framework integrating a calibrated LLM into RL training with uncertainty-modulated guidance and A*-based symbolic trajectories, achieving improved success rate and sample efficiency on MiniGrid-UnlockPickup.
Introduces Multi-Agent Residual In-Context Learning (MARICL), an agentic framework that uses LLM agents to analyze residuals from a base model on tabular data, hypothesize missing structure, and produce explicit correction terms via textual gradient optimization. Across nine benchmarks, MARICL consistently improves over its base model and demonstrates mechanistic generalization in cell-free protein predictions.