# Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

arXiv: https://arxiv.org/abs/2607.08964 · HTML: https://mlsanity.com/paper/2607.08964/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 30 of 31)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [Self-Rewarding Vision-Language Model via Reasoning Decomposition](https://mlsanity.com/paper/2508.19652/) (2025)
- [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows](https://mlsanity.com/paper/2605.27922/) (2026)
- [A Survey on the Optimization of Large Language Model-based Agents](https://mlsanity.com/paper/2503.12434/) (2025)
- [LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces](https://mlsanity.com/paper/2602.14337/) (2026)
- [Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents](https://mlsanity.com/paper/2605.30621/) (2026)
- [From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users](https://mlsanity.com/paper/2508.17281/) (2025)
- [APEX-Agents](https://mlsanity.com/paper/2601.14242/) (2026)
- [Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks](https://mlsanity.com/paper/2603.00077/) (2026)
- [The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break](https://mlsanity.com/paper/2604.11978/) (2026)
- [HCAST: Human-Calibrated Autonomy Software Tasks](https://mlsanity.com/paper/2503.17354/) (2025)
- [SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?](https://mlsanity.com/paper/2606.07682/) (2026)
- [RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following](https://mlsanity.com/paper/2603.25133/) (2026)
- [CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent](https://mlsanity.com/paper/2510.18596/) (2025)
- [Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2604.20987/) (2026)
- [COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows](https://mlsanity.com/paper/2607.01709/) (2026)
- [KLong: Training LLM Agent for Extremely Long-horizon Tasks](https://mlsanity.com/paper/2602.17547/) (2026)

## Built on by (most cited first, 30 of 31)

- [SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning](https://mlsanity.com/paper/2607.14777/) (2026)
- [Recursive Synthesis for Long-Horizon Terminal Tasks](https://mlsanity.com/paper/2608.05466/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks](https://mlsanity.com/paper/2608.06352/) (2026)
- [T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks](https://mlsanity.com/paper/2609.11042/) (2026)
- [The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation](https://mlsanity.com/paper/2607.24720/) (2026)
- [ERASE: EaRly bAckpropagation SchEdule for Faster Training of Modern Recommendation Systems](https://mlsanity.com/paper/2608.18469/) (2026)
- [CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?](https://mlsanity.com/paper/2610.07557/) (2026)
- [FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents](https://mlsanity.com/paper/2608.18423/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model](https://mlsanity.com/paper/2608.22295/) (2026)
- [Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design](https://mlsanity.com/paper/2609.22086/) (2026)
- [Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite](https://mlsanity.com/paper/2610.02826/) (2026)
- [A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching](https://mlsanity.com/paper/2610.10447/) (2026)
- [Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance](https://mlsanity.com/paper/2607.27283/) (2026)
- [Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation](https://mlsanity.com/paper/2609.11115/) (2026)
- [QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling](https://mlsanity.com/paper/2609.16887/) (2026)
- [When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse](https://mlsanity.com/paper/2609.28870/) (2026)
- [Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging](https://mlsanity.com/paper/2609.32303/) (2026)
- [On the Behavioral Traits of LLM Agents](https://mlsanity.com/paper/2609.32776/) (2026)
- [Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses](https://mlsanity.com/paper/2609.34649/) (2026)
- [FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management](https://mlsanity.com/paper/2609.34710/) (2026)
- [Scaling Agentic Data for Long-Horizon Terminal Intelligence](https://mlsanity.com/paper/2610.13166/) (2026)
- [Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress](https://mlsanity.com/paper/2610.14146/) (2026)
- [WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions](https://mlsanity.com/paper/2610.14915/) (2026)
- [SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition](https://mlsanity.com/paper/2610.14966/) (2026)
- [StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents](https://mlsanity.com/paper/2610.17616/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)
- [Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery](https://mlsanity.com/paper/2610.18449/) (2026)
- [Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards](https://mlsanity.com/paper/2610.18868/) (2026)

## Abstract (arXiv)

AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46 long-horizon tasks spanning nine categories, including experiment reproduction, software engineering, multimodal analysis, interactive games, and scientific computing. Each task follows a Terminal-Bench-style setup with a reference solution or simulation engine, but is further decomposed into fine-grained graded subtasks. This design enables dense intermediate rewards and partial credit, allowing evaluation to capture not only whether an agent reaches the final goal, but also how far it progresses on open-ended workflows. Tasks in Long-Horizon-Terminal-Bench typically require hundreds of episodes and minutes to hours of execution, stressing long-horizon planning, long-context management, and iterative debugging rather than one-shot problem solving. We evaluate 15 frontier models and find that agents consume on average 9.9M tokens per task, with roughly 231 episodes and 85.3 minutes of execution time per run, making Long-Horizon-Terminal-Bench more demanding than prior terminal-based benchmarks. Even the strongest tested model achieves 15.2% pass@1 at a partial-reward threshold of 0.95 and 10.9% at a perfect-reward threshold of 1.0, while the mean pass rate across models is 4.3% and 1.7% under the two thresholds, respectively. These results reveal headroom for improvement. We further analyze failure modes and error patterns, and release Long-Horizon-Terminal-Bench to support future progress on long-horizon terminal agents.