# Evaluating Long-Context Reasoning in LLM-Based WebAgents

arXiv: https://arxiv.org/abs/2512.04307 · HTML: https://mlsanity.com/paper/2512.04307/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://mlsanity.com/paper/2305.11854/) (2023)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024)
- [WebCanvas: Benchmarking Web Agents in Online Environments](https://mlsanity.com/paper/2406.12373/) (2024)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [Non-Determinism of "Deterministic" LLM Settings](https://mlsanity.com/paper/2408.04667/) (2024)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents](https://mlsanity.com/paper/2412.13194/) (2024)
- [Personalized LLM Response Generation with Parameterized Memory Injection](https://mlsanity.com/paper/2404.03565/) (2024)

## Built on by (most cited first, 15 of 15)

- [Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty](https://mlsanity.com/paper/2605.11436/) (2026)
- [WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning](https://mlsanity.com/paper/2601.03164/) (2026)
- [PABU: Progress-Aware Belief Update for Efficient LLM Agents](https://mlsanity.com/paper/2602.09138/) (2026)
- [OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions](https://mlsanity.com/paper/2602.05843/) (2026)
- [From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences](https://mlsanity.com/paper/2604.10332/) (2026)
- [Diagnosing and Mitigating Context Rot in Long-horizon Search](https://mlsanity.com/paper/2606.29718/) (2026)
- [Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents](https://mlsanity.com/paper/2607.05775/) (2026)
- [TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews](https://mlsanity.com/paper/2605.26911/) (2026)
- [HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification](https://mlsanity.com/paper/2606.18671/) (2026)
- [World-Model Collapse as a Phase Transition](https://mlsanity.com/paper/2606.31399/) (2026)
- [Signal-Driven Observation for Long-Horizon Web Agents](https://mlsanity.com/paper/2606.06708/) (2026)
- [NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement](https://mlsanity.com/paper/2607.26633/) (2026)
- [DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2609.18135/) (2026)
- [MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents](https://mlsanity.com/paper/2609.19059/) (2026)
- [Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents](https://mlsanity.com/paper/2609.33304/) (2026)

## Abstract (arXiv)

As large language model (LLM)-based agents become increasingly integrated into daily digital interactions, their ability to reason across long interaction histories becomes crucial for providing personalized and contextually aware assistance. However, the performance of these agents in long context scenarios, particularly for action-taking WebAgents operating in realistic web environments, remains largely unexplored. This paper introduces a benchmark for evaluating long context reasoning capabilities of WebAgents through sequentially dependent subtasks that require retrieval and application of information from extended interaction histories. We develop a novel evaluation framework that simulates multi-session user interactions by injecting irrelevant task trajectories between dependent subtasks, creating contexts ranging from 25,000 to 150,000 tokens. Through extensive evaluation of four popular models, Claude-3.7, GPT-4.1, Llama 4, and o4-mini, we observe a dramatic performance degradation as context length increases, with success rates dropping from 40-50% in baseline conditions to less than 10% in long context scenarios. Our detailed error analysis reveals that agents primarily fail due to getting stuck in loops and losing track of original task objectives. We further propose an implicit RAG approach that provides modest improvements by generating task-relevant summaries, though fundamental limitations in long context reasoning persist. These findings highlight critical challenges for deploying WebAgents in realistic, long-term user interaction scenarios and provide insights for developing more robust agent architectures capable of maintaining coherent task execution across extended contexts.