SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
Agent skill acquisition for large language models via CycleQD
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
background 2representative citing papers
GrandCode is the first AI system to consistently beat all human participants and place first in live Codeforces competitive programming contests.
On a widened 1536-dimensional substrate, a router rewrite explains the full +0.0426 nat log-PPL gain of an evolutionary MoLoRA system while the lifecycle component imposes a -0.028 nat drag and the headline full-system gain fails to reach significance at n=3 seeds.
citing papers explorer
-
SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
SkillGraph jointly evolves agent skills and collaboration topologies in multi-agent vision-language systems using a multimodal graph transformer and a skill designer, yielding consistent performance gains on benchmarks.
-
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
GrandCode is the first AI system to consistently beat all human participants and place first in live Codeforces competitive programming contests.
-
Decomposing Evolutionary Mixture-of-LoRA Architectures: The Routing Lever, the Lifecycle Penalty, and a Substrate-Conditional Boundary
On a widened 1536-dimensional substrate, a router rewrite explains the full +0.0426 nat log-PPL gain of an evolutionary MoLoRA system while the lifecycle component imposes a -0.028 nat drag and the headline full-system gain fails to reach significance at n=3 seeds.