GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

arXiv:2609.38923 · cs.CL · Submitted 2026-09-30 · Read on arXiv

cs.CL

Submitted: 2026-09-30

Updated: 2026-10-04

Code: https://github.com/nousresearch/hermes-agent

Terminology

• Verification — 13× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Core — 5× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• APEX — 2× in this paper · explained in 1 episode
• Ablation — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
• TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
• Toward Scalable Terminal Task Synthesis via Skill Graphs
• CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
• R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
• GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
• OpenThoughts-Agent: Data Recipes for Agentic Models
• TaskCraft: Automated Generation of Agentic Tasks
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
• APEX-Agents
• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
• How Well Does Agent Development Reflect Real-World Work?
• AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
• SWE-smith: Scaling Data for Software Engineering Agents
• Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
• EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent
• NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
• SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering