To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents

arXiv:2605.18882 · cs.LG, cs.AI · Submitted 2026-05-16 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-05-16

Updated: 2026-10-06

Code: https://github.com/SKURA502/agent-sae

Terminology

• Accuracy — 5× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Intrinsic Bias Hypothesis — 1× in this paper
• Sparse Autoencoders (SAEs) — 1× in this paper · explained in 3 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• OpenAI GPT-5 System Card
• Gorilla: Large Language Model Connected with Massive APIs
• Gemma 3 Technical Report
• Ministral 3
• MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
• Do LLMs Know Their Vulnerable Scenarios?
• Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling

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