The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agents

arXiv:2609.34988 · cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Benchmark — 14× in this paper · explained in 2 episodes
• Trace — 8× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 7× in this paper
• Self-Evolving Agents — 7× in this paper · explained in 2 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• International Conference on Machine Learning — 4× in this paper
• Generative AI — 3× in this paper · explained in 2 episodes
• In Conference on Language Modeling — 3× in this paper
• Agent Workflow Memory — 2× in this paper
• Agentic System — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Provenance — 2× in this paper · explained in 4 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Temporal Abstraction — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• Recursive Partitioning for Heterogeneous Causal Effects
• Program Synthesis with Large Language Models
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
• Reinforcement Learning for Long-Horizon Interactive LLM Agents
• Evaluating Large Language Models Trained on Code
• AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning
• Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
• Automated Design of Agentic Systems
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• Self-Refine: Iterative Refinement with Self-Feedback
• CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization
• Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
• Symbolic Learning Enables Self-Evolving Agents
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
• AgentSquare: Automatic LLM Agent Search in Modular Design Space

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering