Tau-2Bench

'Tau-2Bench' is a benchmark used to evaluate the generalization capabilities of agentic reasoning systems in tool-calling environments.

Papers using Tau-2Bench (16)

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning2026Towards General Agentic Intelligence via Environment Scaling2025PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents2026Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents2026Proper Scoring Rules for Agentic Uncertainty Quantification2026SkillsInjector: Dynamic Skill Context Construction for LLM Agents2026MemGym: a Long-Horizon Memory Environment for LLM Agents2026MAVEN: Improving Generalization in Agentic Tool Calling2026Step 3.5 Flash: Open Frontier-level Intelligence With 11B Active Parameters2026Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors2026TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training2026EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL2026Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents2026AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning2025On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset2025Toolorchestra: Elevating Intelligence Via Efficient Model And Tool Orchestration2025