aiqbench analysis
This paper introduces A-SR, a novel agentic framework for symbolic regression that replaces monolithic search loops with role-conditioned coordination protocols to improve formula discovery accuracy. By routing failure traces and validity diagnostics between specialized agents without updating base model parameters, the method achieves significant performance gains on both synthetic benchmarks and real-world scientific tasks. The approach demonstrates how architectural shifts in agent orchestration can enhance LLM capabilities for mathematical reasoning and equation generation.
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
arXiv:2608.04872v1 Announce Type: cross Abstract: Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory. During search, evaluator feedback characterizes reliability and productivity, updates role-level utilities, and routes elite motifs, failure traces, and validity diagnostics to different agents. The framework self-evolves at two timescales: within a run, it adapts the search process without updating LLM parameters; across runs, recorded trajectories can be distilled into open-source LLMs as role-conditioned proposal priors. Averaged over the four LSR-Synth scientific domains in LLM-SRBench, A-SR improves Acc@0.01 over baselines from 25.79% to 48.30% with Llama3.1-8B, while A-SR-LoRA improves the corresponding Qwen3-4B result from 24.58% to 38.29%. On four real-world scientific discovery tasks, A-SR obtains the best in-distribution or out-of-distribution normalized mean squared error on 7 of 8 reported metrics.
Abstract:Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory. During search, evaluator feedback characterizes reliability and productivity, updates role-level utilities, and routes elite motifs, failure traces, and validity diagnostics to different agents. The framework self-evolves at two timescales: within a run, it adapts the search process without updating LLM parameters; across runs, recorded trajectories can be distilled into open-source LLMs as role-conditioned proposal priors. Averaged over the four LSR-Synth scientific domains in LLM-SRBench, A-SR improves Acc@0.01 over baselines from 25.79% to 48.30% with Llama3.1-8B, while A-SR-LoRA improves the corresponding Qwen3-4B result from 24.58% to 38.29%. On four real-world scientific discovery tasks, A-SR obtains the best in-distribution or out-of-distribution normalized mean squared error on 7 of 8 reported metrics.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2608.04872 [cs.CL]
(or arXiv:2608.04872v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.04872 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 280 words
Related coverage
Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis
arXiv · Sep 30, 2026
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis
arXiv · Aug 27, 2026
AgentOps: Operationalize agentic AI at scale with Amazon Bedrock AgentCore
AWS · Jun 1, 2026
GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Meta Engineering · Aug 3, 2026