# How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making

arXiv: https://arxiv.org/abs/2609.01660 · HTML: https://mlsanity.com/paper/2609.01660/

## Key facts

- Cited by 1 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 20 of its 22 references that are in the map.
- First posted on arXiv 31 Aug 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, 20 of 20)

- [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)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [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)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Is Smaller Greener? Right-Sizing Language Models for Agentic AI](https://mlsanity.com/paper/2610.19345/) (2026)

## Abstract (arXiv)

Production deployments of large language model (LLM) agents remain unreliable on long, multi-step workflows even as benchmark success rates climb steadily. We argue this gap is largely an artifact of task horizon: benchmarks are dominated by short-to-medium horizons where success remains high, while production workloads demand an order of magnitude more dependent steps. We measure the effect directly, characterizing the shape of agent degradation and disentangling its cause across a large controlled study spanning nine models, six open models from 1.2B to 671B parameters, and three deployed proprietary systems; four task families, including a genuinely agentic tool-use loop; five horizons; and three context regimes. Task success follows a geometric law governed by a single per-step reliability parameter, which rises with model scale but saturates well below 1 even for the strongest models, guaranteeing eventual collapse at sufficiently long horizons. The effect is sharpest on the agentic task, where every model tested, including widely deployed systems, falls from near-perfect success to near zero within sixteen steps of (n=10,664 analyzed trajectories. Degradation is driven by step count rather than context length: bounding the context window steepens decay rather than easing it (logit slope -0.69 vs. -0.44), p=3x10-6), contradicting a lost-in-the-middle explanation and warning against a common production shortcut. Projecting measured reliability onto representative benchmark horizons quantifies a substantial gap between benchmark and production conditions, from 0.42 at GAIA-length horizons to 0.24 at hundred-step production horizons. For teams responsible for agent orchestration and reliability at scale, these results argue for horizon-aware evaluation and reliability budgeting in place of aggregate pass-rate metrics. Code, prompts, seeds, and raw trajectories are released.