LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks

2026-02-28

AI Summary

This work addresses the scarcity of logically rigorous and verifiable agent training data for large language models in complex, stateful environments. To this end, the authors propose LOGIGEN, a framework that synthesizes high-fidelity task trajectories through a three-agent collaborative, logic-driven mechanism. By integrating hard-coded policy grounding, forward logical generation, and deterministic state verification, LOGIGEN ensures causal consistency and adherence to real-world constraints. Using 20,000 multi-domain trajectories generated by this approach, the LOGIGEN-32B(RL) model—fine-tuned via supervised learning and reinforced with state-based rewards—achieves a 79.5% task success rate on the τ²-Bench, substantially outperforming baseline models (40.7%). These results demonstrate the effectiveness and superiority of LOGIGEN in enabling verifiable agent training.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise state-transition objectives. However, this paradigm is bottlenecked by data scarcity, as existing tool-centric reverse-synthesis pipelines fail to capture the rigorous logic of real-world applications. We introduce \textbf{LOGIGEN}, a logic-driven framework that synthesizes verifiable training data based on three core pillars: \textbf{Hard-Compiled Policy Grounding}, \textbf{Logic-Driven Forward Synthesis}, and \textbf{Deterministic State Verification}. Specifically, a Triple-Agent Orchestration is employed: the \textbf{Architect} compiles natural-language policy into database constraints to enforce hard rules; the \textbf{Set Designer} initializes boundary-adjacent states to trigger critical policy conflicts; and the \textbf{Explorer} searches this environment to discover causal solution paths. This framework yields a dataset of 20,000 complex tasks across 8 domains, where validity is strictly guaranteed by checking exact state equivalence. Furthermore, we propose a verification-based training protocol where Supervised Fine-Tuning (SFT) on verifiable trajectories establishes compliance with hard-compiled policy, while Reinforcement Learning (RL) guided by dense state-rewards refines long-horizon goal achievement. On $τ^2$-Bench, LOGIGEN-32B(RL) achieves a \textbf{79.5\% success rate}, substantially outperforming the base model (40.7\%). These results demonstrate that logic-driven synthesis combined with verification-based training effectively constructs the causally valid trajectories needed for next-generation agents.

Problem

• data scarcity
• stateful environments
• logic-driven synthesis
• verifiable tasks
• autonomous agents

Innovation

• Logic-Driven Synthesis
• Verifiable Agentic Tasks
• Hard-Compiled Policy Grounding
• Deterministic State Verification
• Triple-Agent Orchestration