Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined control flows. This limitation restricts adaptive reasoning, blocks cross-paradigm transfer, and discards valuable execution feedback. We propose AlgoEvo, a unified agentic framework that transforms automated algorithm discovery into an interactive, knowledge-accumulating process. An autonomous agent dynamically inspects, diagnoses, and edits code based on runtime feedback. A design skill hub decouples paradigm-specific knowledge from the core discovery engine, allowing a single workflow to seamlessly handle single-objective, multi-objective, and multi-component design. Meanwhile, a hierarchical experience mechanism organizes search trajectories into a task-level tree to guide exploration and consolidates cross-task patterns into reusable skills. Across six representative benchmark tasks, AlgoEvo matches or surpasses specialized methods with substantially fewer evaluations and reduced token consumption, demonstrating strong intra-task accumulation, cross-task transfer, and the ability to reproduce or exceed existing state-of-the-art performance through flexible skill activation.
AutoScientist-Quant, a self evolving search process that regards quantitative research as one budgeted search problem, is presented, a self evolving search process that regards quantitative research as one budgeted search problem.
Zong-Qian Li, Yaoyiran Li, Yao-Hui Guo et al.· 2 citations
ASPO introduces an Adaptive Query-Selection Mechanism (AQSM) that focuses training on queries at the policy's competence boundary: those it can solve but not yet reliably, and introduces substructure-level rewards that measure output-quality gains within each action's descendant subgraph.
ReASearch is presented, a unified framework for reasoning-driven optimization in which the agent autonomously decides what to evaluate, how to diagnose failures, which edits to make, and when to verify or restart.
Jun-Bo Li, Bo-Yi Liu, Can-Wen Xu et al.· 1 citation
This paper proposes AgentExecutor, a novel multi-agent framework for partial code execution that is Supported by the power of LLM agents who can think, act, and get feedback iteratively, and is able to autonomously explore a richer action space, enabling diverse operations such as creating resource files and resolving...
Junkai Chen, Cheng-Ran Yang, Xing Hu et al.· 0 citations