Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs
Summary
Deliberate Evolution (DE) is an agentic framework that improves LLM-based symbolic regression by decoupling candidate generation from search control, using adaptive operators, structural diagnosis tools, and reflective memory to achieve better results with only 40% of the standard sample budget.
View Cached Full Text
Cached at: 06/05/26, 02:13 AM
# Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs Source: [https://arxiv.org/abs/2606.04360](https://arxiv.org/abs/2606.04360) [View PDF](https://arxiv.org/pdf/2606.04360) > Abstract:Symbolic regression \(SR\) discovers compact mathematical expressions from data, yet recent LLM\-based evolutionary methods remain sample\-inefficient because they rely mainly on scalar feedback such as MSE\. We identify a core limitation: existing methods conflate candidate proposal with search guidance, requiring the LLM to infer how to evolve an expression, diagnose its errors, and reuse past experience from a single score\. To address this, we propose Deliberate Evolution \(DE\), an agentic framework that decouples symbolic generation from search control\. DE guides LLM proposals with adaptive operators for search direction, analytical tools for structural diagnosis, and reflective memory for trajectory\-level experience\. Experiments on LLM\-SRBench show that DE consistently outperforms representative LLM\-based SR baselines across diverse scientific domains while using only 40% of the standard sample budget\. ## Submission history From: Xinyu Pang \[[view email](https://arxiv.org/show-email/4ae232aa/2606.04360)\] **\[v1\]**Wed, 3 Jun 2026 02:22:16 UTC \(4,845 KB\)
Similar Articles
@Kevin_GuoweiXu: How should LLMs sample on hard reasoning problems during post-training and inference where direct rollouts rarely produ…
Introduces BES (Bidirectional Evolutionary Search), a search framework for LLMs that combines forward candidate evolution with backward goal decomposition to improve sampling on hard reasoning problems during post-training and inference.
EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics
EvoMD-LLM reformulates reactive molecular dynamics trajectories as symbolic temporal sequences, enabling LLMs to model species evolution over time through fine-tuning and temporal scaffolding, achieving up to 66.14% accuracy and interpretable predictions.
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
MetaEvo proposes a two-stage framework for continual evolution of LLM-based agents, using preference-based optimization to enhance principle abstraction and modular architecture for experience reuse, outperforming strong baselines on reasoning benchmarks.
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
CoEvolve proposes an agent-data mutual evolution framework for training LLM agents through closed-loop, interaction-driven learning that adapts both the agent and its training data distribution. The method extracts feedback signals from rollout trajectories to guide LLM-based task synthesis, demonstrating significant improvements (15-19% absolute gains) across multiple Qwen models on AppWorld and BFCL benchmarks.
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
LC-ERD is a framework that mines latent logic from LLM-generated reasoning chains to decompose global rewards into step-level signals, enabling self-evolving reasoning without human annotation. It addresses label noise, coarse supervision, and distributional collapse via variational logic potential and multi-agent value decomposition.