# What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels

arXiv: https://arxiv.org/abs/2608.22960 · HTML: https://mlsanity.com/paper/2608.22960/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 24 Aug 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, 29 of 29)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [RUDDER: Return Decomposition for Delayed Rewards](https://mlsanity.com/paper/1806.07857/) (2018)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Calibrating Large Language Models Using Their Generations Only](https://mlsanity.com/paper/2403.05973/) (2024)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs](https://mlsanity.com/paper/2408.09955/) (2024)
- [TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2407.10114/) (2024)
- [STeCa: Step-level Trajectory Calibration for LLM Agent Learning](https://mlsanity.com/paper/2502.14276/) (2025)
- [Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2604.22708/) (2026)
- [LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals](https://mlsanity.com/paper/2604.05655/) (2026)
- [Calibrating LLM Confidence by Probing Perturbed Representation Stability](https://mlsanity.com/paper/2505.21772/) (2025)
- [Deep Bayesian Active Learning for Preference Modeling in Large Language Models](https://mlsanity.com/paper/2406.10023/) (2024)
- [Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs](https://mlsanity.com/paper/2511.04869/) (2025)
- [MEMENTO: Teaching LLMs to Manage Their Own Context](https://mlsanity.com/paper/2604.09852/) (2026)
- [RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation](https://mlsanity.com/paper/2501.08617/) (2025)
- [Counterfactual Token Generation in Large Language Models](https://mlsanity.com/paper/2409.17027/) (2024)
- [Gumbel Counterfactual Generation From Language Models](https://mlsanity.com/paper/2411.07180/) (2024)
- [Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning](https://mlsanity.com/paper/2509.26578/) (2025)
- [InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning](https://mlsanity.com/paper/2601.14209/) (2026)
- [Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles](https://mlsanity.com/paper/2501.03991/) (2025)
- [Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems](https://mlsanity.com/paper/2506.10060/) (2025)
- [ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents](https://mlsanity.com/paper/2605.20251/) (2026)
- [KnowThyself: An Agentic Assistant for LLM Interpretability](https://mlsanity.com/paper/2511.03878/) (2025)

## Abstract (arXiv)

Coding agents are increasingly evaluated not only by whether they solve a task, but also by how they execute it. However, existing process-level evaluations often treat action prediction, task uncertainty, and step attribution as if they were the same problem, which makes it unclear what such evaluations actually measure. In this paper, we introduce a measurement framework for process evaluation in coding agents and instantiate step-level causal attribution with SCAE, a replay-based estimator derived from a structural causal model of agent execution. Our framework combines prefix-conditioned identification, replay/intervention-based estimation, and controlled judge-information manipulation to study process evaluation at the action, task, and step levels. Experiments on 499 file-localization episodes from 12 repositories show that next actions are driven primarily by execution provenance rather than code-graph transitions, execution uncertainty is structured at the task rather than step level, and full-trace judges exhibit systematic collider bias, suggesting that current process evaluation often measures semantic relevance rather than certified causal contribution.