# CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

arXiv: https://arxiv.org/abs/2608.06352 · HTML: https://mlsanity.com/paper/2608.06352/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 63 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 30 of 45)

- [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)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [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)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://mlsanity.com/paper/2306.14898/) (2023)
- [CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark](https://mlsanity.com/paper/2409.11363/) (2024)
- [Endless Terminals: Scaling RL Environments for Terminal Agents](https://mlsanity.com/paper/2601.16443/) (2026)
- [On Data Engineering for Scaling LLM Terminal Capabilities](https://mlsanity.com/paper/2602.21193/) (2026)
- [LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces](https://mlsanity.com/paper/2602.14337/) (2026)
- [Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments](https://mlsanity.com/paper/2602.01244/) (2026)
- [Tmax: A simple recipe for terminal agents](https://mlsanity.com/paper/2606.23321/) (2026)
- [Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading](https://mlsanity.com/paper/2607.08964/) (2026)
- [TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents](https://mlsanity.com/paper/2602.07274/) (2026)
- [SWE-World: Building Software Engineering Agents in Docker-Free Environments](https://mlsanity.com/paper/2602.03419/) (2026)
- [CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion](https://mlsanity.com/paper/2602.10999/) (2026)
- [SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training](https://mlsanity.com/paper/2602.03411/) (2026)
- [Immersion in the GitHub Universe: Scaling Coding Agents to Mastery](https://mlsanity.com/paper/2602.09892/) (2026)
- [BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?](https://mlsanity.com/paper/2603.03194/) (2026)
- [Composer 2 Technical Report](https://mlsanity.com/paper/2603.24477/) (2026)

## Built on by (most cited first, 8 of 8)

- [Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments](https://mlsanity.com/paper/2609.04148/) (2026)
- [T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks](https://mlsanity.com/paper/2609.11042/) (2026)
- [FrogNano: Training a 4B Coding Agent via Online Task Synthesis](https://mlsanity.com/paper/2609.07925/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [Agent-Editing World Model: Rethinking World Modeling for LLM Agents](https://mlsanity.com/paper/2609.28416/) (2026)
- [Scaling Agentic Data for Long-Horizon Terminal Intelligence](https://mlsanity.com/paper/2610.13166/) (2026)
- [AutoEnvScaling: Automating the Data Flywheel with Terminal Agents](https://mlsanity.com/paper/2610.14163/) (2026)
- [WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions](https://mlsanity.com/paper/2610.14915/) (2026)

## Abstract (arXiv)

Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/weak-fail relation; both operationalize a solver-relative learnable zone anchored in demonstrated solvability. Using CalibForge, we construct 5,431 calibrated terminal tasks. Our ablations show that both strategies yield more effective supervision than authoring and validation alone or ordinary single-solver feedback. Models trained on the full collection achieve 32.58% and 47.57% on Terminal-Bench 2.0. The largest improvements over the corresponding base model reach 24.71 percentage points on Terminal-Bench 2.0, 27.68 points on SWE-bench Pro, and 30.04 points on Doc2Repo. Together, these results support solver-relative learnability as a practical target for constructing effective and transferable agent training data.