MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
Mermaidflow: Redefining agentic workflow generation via safety-constrained evolutionary programming
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.AI 3verdicts
UNVERDICTED 3representative citing papers
NSI lifts interaction traces into logic programs to enable few-shot skill induction and adaptation for long-horizon agentic tasks.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
citing papers explorer
-
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
-
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
NSI lifts interaction traces into logic programs to enable few-shot skill induction and adaptation for long-horizon agentic tasks.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.