mlsanityData to 14 Oct 2026

Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course

arXiv 2609.08832 ↗First posted 8 Sep 2026cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

also in 1 more
Abstract (arXiv)

Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains largely unaddressed. When given the same task five times, a ReAct agent on the AppWorld benchmark using GPT-4.1 succeeds in all five runs only 53% of the time, even though its per-run pass rate averages 77%. We call this 24-point shortfall the consistency gap, and we argue that addressing it is a precondition for trustworthy AI agent deployment. We present a self-evolving agent framework that reduces this gap by identifying unstable, low-consistency steps in agent trajectories and converting them into episodic memory the agent can draw on in future runs. At its core is a Consistency Analyzer that pinpoints where and why a trajectory is likely to flip across executions, and a Guideline Generator that converts the diagnosis into targeted guidelines, committed to memory and injected into future agent executions on similar tasks. On AppWorld with ReAct/GPT-4.1, our framework raises the fraction of tasks that succeed in all five runs by +16 points on same-task evaluation and +13 points on similar-task generalization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 16 of its 26 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

16 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems9 Mar

Other references · 15

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  5. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  6. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  7. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  8. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  9. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  10. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 101
  11. 2026Towards a Science of AI Agent Reliabilitycited by 65
  12. 2026Trajectory-Informed Memory Generation for Self-Improving Agent Systemscited by 17
3 more
  1. 2026TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agentscited by 15
  2. 2025Agentic AI Process Observability: Discovering Behavioral Variabilitycited by 10
  3. 2026AgentStepper: Interactive Debugging of Software Development Agentscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
  2. 2025Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm
  3. 2026MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
  4. 2026Consistent Plan-Act for Long-Horizon Agentic Tasks
  5. 2026OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
  6. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  7. 2026Self-Designed Evaluators and Warm Memory for Long-Horizon Agents
  8. 2026Measuring Cross-Task Behavioral Consistency in Language Model Agents