Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

CalibForge: Using Solver Behavior to Calibrate Terminal Tasks for Agent Training

AI By Crimson AI Hugging Face Papers 8 August 2026 · 00:00 22 views
Share: X Telegram

Hugging Face researchers introduce CalibForge, a system that calibrates terminal tasks using solver feedback to create a 'learnable zone' for training agents, achieving significant gains on Terminal-Bench 2.0 and other benchmarks.

CalibForge: Using Solver Behavior to Calibrate Terminal Tasks for Agent Training

Key points

Training terminal agents requires tasks that are not just solvable but appropriately challenging for learning. Executable validation alone doesn't reveal how a task behaves relative to a given solver. In a new paper, Hugging Face researchers present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration.

CalibForge employs two calibration strategies: multi-solver calibration targets disagreement within a heterogeneous solver pool, while contrastive solver calibration targets a designated strong-pass/weak-fail relation. Both operationalize a solver-relative learnable zone anchored in demonstrated solvability.

Using CalibForge, the team constructed 5,431 calibrated terminal tasks. 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. These results support solver-relative learnability as a practical target for constructing effective and transferable agent training data.

The work is available on Hugging Face, with model collections and code on GitHub. Related papers include CLI-Universe and SETA, which also explore task synthesis for terminal agents.

BenchmarkImprovement (points)
Terminal-Bench 2.024.71
SWE-bench Pro27.68
Doc2Repo30.04
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1