conftrace_

multi-turn exploration

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

tool-calling agent (1) complex user intent (1) tool-call trajectory (1) coverage (1) representational assumptions (1) spannersampling (1) pre-trained model (1) synthetic data generation (1) policy learning (1)

Papers

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents ACL 2026 Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration COLT 2025