CARE-PO: Controllable Tool-Call Efficiency for LLM Agents
cs.LG, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-12
Terminology
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Tunable Tool-Call Rates in LLM Agents via Representation Steering
- The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
- Inference-Time Budget Control for LLM Search Agents
- ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
- Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
- Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents
- Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
- Qwen3 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
- Acting Less is Reasoning More! Teaching Model to Act Efficiently
- To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
- Rethinking Deep Research from the Perspective of Web Content Distribution Matching
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis