WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
- Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
- DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
- EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- SPADE: Self-Play in Adaptive Synthetic Executable Environments
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- AutomationBench
- Scaling Agentic Capabilities via Grounded Interaction Synthesis
- ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
- EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
- Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
- PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems