AlphaContext generates psychometric contexts for creativity assessment via hypertree outlines, MCTS filling, MAP-Elites evolution, and assessment-guided refinement, reporting an average 8% gain over prior methods on six quality metrics.
Yichun Feng, Jiawei Wang, Lu Zhou, Zhen Lei, and Yixue Li
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
TeamLLM improves LLM performance on multi-step contextualized tasks by using four human-like team roles and a three-phase collaboration process, demonstrated on the new CGPST benchmark.
AGC-Bench introduces a multi-domain creativity benchmark for LLMs, recovers a general 'c' factor explaining 81.5% of variance, and finds humans still outperform top models on matched tasks.
citing papers explorer
-
AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment
AlphaContext generates psychometric contexts for creativity assessment via hypertree outlines, MCTS filling, MAP-Elites evolution, and assessment-guided refinement, reporting an average 8% gain over prior methods on six quality metrics.
-
TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks
TeamLLM improves LLM performance on multi-step contextualized tasks by using four human-like team roles and a three-phase collaboration process, demonstrated on the new CGPST benchmark.
-
AGC-Bench: Measuring Artificial General Creativity
AGC-Bench introduces a multi-domain creativity benchmark for LLMs, recovers a general 'c' factor explaining 81.5% of variance, and finds humans still outperform top models on matched tasks.