# TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents

arXiv: https://arxiv.org/abs/2602.02196 · HTML: https://mlsanity.com/paper/2602.02196/

## Key facts

- Cited by 7 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 29 of its 40 references that are in the map.
- First posted on arXiv 2 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, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (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)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)
- [SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.02479/) (2025)
- [LocAgent: Graph-Guided LLM Agents for Code Localization](https://mlsanity.com/paper/2503.09089/) (2025)
- [Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration](https://mlsanity.com/paper/2310.00280/) (2023)
- [Vision-Language Models Can Self-Improve Reasoning via Reflection](https://mlsanity.com/paper/2411.00855/) (2024)
- [ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data](https://mlsanity.com/paper/2509.15221/) (2025)
- [ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows](https://mlsanity.com/paper/2505.19897/) (2025)
- [Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction](https://mlsanity.com/paper/2506.07976/) (2025)
- [Self-Improving LLM Agents at Test-Time](https://mlsanity.com/paper/2510.07841/) (2025)
- [AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents](https://mlsanity.com/paper/2404.06411/) (2024)
- [Environment Scaling for Interactive Agentic Experience Collection: A Survey](https://mlsanity.com/paper/2511.09586/) (2025)
- [Beyond Optimism: Exploration With Partially Observable Rewards](https://mlsanity.com/paper/2406.13909/) (2024)
- [Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs](https://mlsanity.com/paper/2509.23166/) (2025)
- [A3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation](https://mlsanity.com/paper/2601.09274/) (2026)

## Built on by (most cited first, 7 of 7)

- [How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings](https://mlsanity.com/paper/2604.04323/) (2026)
- [OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions](https://mlsanity.com/paper/2602.05843/) (2026)
- [SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction](https://mlsanity.com/paper/2606.04691/) (2026)
- [MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning](https://mlsanity.com/paper/2606.11537/) (2026)
- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)
- [World State Generator](https://mlsanity.com/paper/2609.24744/) (2026)
- [Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training](https://mlsanity.com/paper/2609.33335/) (2026)

## Abstract (arXiv)

Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why TTI succeed or fail remain poorly understood, and existing evaluation metrics fail to capture their task optimization efficiency, behavior adaptation after erroneous actions, and the specific utility of working memory for task completion. To address these gaps, we propose Test-time Improvement Diagnostic Evaluation (TIDE), an agent-agnostic and environment-agnostic framework that decomposes TTI into three comprehensive and interconnected dimensions. The framework measures (1) the overall temporal dynamics of task completion and (2) identifies whether performance is primarily constrained by recursive looping behaviors or (3) by burdensome accumulated memory. Through extensive experiments across diverse agents and environments, TIDE highlights that improving agent performance requires more than scaling internal reasoning, calling for explicitly optimizing the interaction dynamics between the agent and the environment.