# "LLM Agent Performance" Is Not a Single Evaluation Target

arXiv: https://arxiv.org/abs/2602.03238 · HTML: https://mlsanity.com/paper/2602.03238/

## Key facts

- Cited by 3 papers in the map (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 19 of its 40 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (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)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards](https://mlsanity.com/paper/2402.01781/) (2024)
- [Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant](https://mlsanity.com/paper/2502.01390/) (2025)
- [Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks](https://mlsanity.com/paper/2405.01719/) (2024)

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

- [UniACE: A Unified Framework for Evaluating LLM Agentic Capabilities](https://mlsanity.com/paper/2605.27898/) (2026)
- [Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts](https://mlsanity.com/paper/2609.18366/) (2026)
- [What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents](https://mlsanity.com/paper/2609.32318/) (2026)

## Abstract (arXiv)

LLM agent benchmark scores are shaped not only by the model but also by the agent harness, environment, evaluator, and inference budget. Unified execution controls these non-model factors by evaluating candidate models under the same configuration, making observed differences more attributable to the models themselves. However, model comparison is only one use of agent benchmarks. Other evaluations compare complete agent systems or test whether a fixed model or system remains stable across predeclared changes in its operating conditions. These results can all be reported under the common label of "LLM agent performance." Our position is that "LLM agent performance" does not denote a single evaluation target. Model comparisons under a reference stack and comparisons of complete agent systems answer different questions, while robustness asks whether either conclusion persists across predeclared conditions. The claim supported by a score therefore depends on the declared candidate boundary and condition policy. We derive implications for leaderboards, result reporting, and benchmark versioning, showing how distinguishing these classes preserves fair comparison while accommodating system innovation and robustness analysis.