TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training

arXiv:2603.01714 · cs.LG, cs.CL · Submitted 2026-03-02 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-03-02

Updated: 2026-10-13

Terminology

• Covariate Shift — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Supervised Fine-Tuning — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
• Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
• ACEBench: Who Wins the Match Point in Tool Usage?
• Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization
• Rethinking LLM Training through Information Geometry and Quantum Metrics
• WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment
• Towards General Agentic Intelligence via Environment Scaling
• Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training
• Interaction Dynamics as a Reward Signal for LLMs
• Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
• Tree Search for LLM Agent Reinforcement Learning
• Exploring Expert Failures Improves LLM Agent Tuning
• ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents
• TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
• Simulating Environments with Reasoning Models for Agent Training
• ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
• CARL: Criticality-Aware Agentic Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks