Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay

arXiv:2608.19760 · cs.LG, cs.AI, cs.CL · Submitted 2026-08-20 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2026-08-20

Updated: 2026-08-25

Comments: 52 pages, 6 figures. Pre-registered; frozen analysis plans and prompts included in the appendices

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fidelity — 3× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks