# Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents

arXiv: https://arxiv.org/abs/2609.12205 · HTML: https://mlsanity.com/paper/2609.12205/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 26 of 26)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [The illusion of artificial inclusion](https://mlsanity.com/paper/2401.08572/) (2024)
- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions](https://mlsanity.com/paper/2605.29442/) (2026)
- [Comparing Human Oversight Strategies for Computer-Use Agents](https://mlsanity.com/paper/2604.04918/) (2026)
- [Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents](https://mlsanity.com/paper/2606.05391/) (2026)
- [LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents](https://mlsanity.com/paper/2608.18398/) (2026)
- [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://mlsanity.com/paper/2602.16844/) (2026)
- ["I'm Not Reading All of That": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants](https://mlsanity.com/paper/2603.14225/) (2026)
- [TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents](https://mlsanity.com/paper/2605.09934/) (2026)
- [Artifact-centered Claim-aware Observability for Autonomous Scientific Agents](https://mlsanity.com/paper/2608.18312/) (2026)
- [HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification](https://mlsanity.com/paper/2606.18671/) (2026)

## Built on by (most cited first, 3 of 3)

- [Empty Commitments: When Agents Promise What They Cannot Deliver](https://mlsanity.com/paper/2610.01045/) (2026)
- [Measuring and Reducing Unusable Replies of LLM Agents](https://mlsanity.com/paper/2610.19659/) (2026)
- [What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports](https://mlsanity.com/paper/2610.20003/) (2026)

## Abstract (arXiv)

When a coding agent finishes a task, the developer reviews a summary the agent wrote about itself, not a display someone designed. We ask how much of the agent's work that summary carries, and whether it drifts toward the plan the agent stated when execution departed from it. Across 5,851 real developer sessions and 355,942 tool calls, a self-report referred to about one action in eleven, and a reader working from the report alone recovered roughly a fifth of the action log. Neither figure depended on whether the session later needed human correction. Reports did not generally resemble the stated plan more than the executed one, but they did so increasingly as execution diverged from the plan. We hand-validate both measurement steps that use a language model, report the one that failed alongside the one that passed, and draw conclusions only from measures that survived.