Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents

arXiv:2609.29095 · cs.LG, cs.AI, cs.SE · Submitted 2026-09-24 · Read on arXiv

cs.LG, cs.AI, cs.SE

Submitted: 2026-09-24

Updated: 2026-09-24

Code: https://github.com/gssanjana4/idempotencybench

Terminology

• Verification — 24× in this paper · explained in 2 episodes
• Benchmark — 19× in this paper · explained in 2 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Trace — 4× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Agentic System — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• In International Conference on Learning Representations — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning
• Cordon: Semantic Transactions for Tool-Using LLM Agents
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
• ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions
• Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
• AI Agents That Matter
• WAREX: Web Agent Reliability Evaluation on Existing Benchmarks
• Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures
• AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP
• GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications
• Towards a Science of AI Agent Reliability
• Identifying the Risks of LM Agents with an LM-Emulated Sandbox
• Reflexion: Language Agents with Verbal Reinforcement Learning
• ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems
• AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
• PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases

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