Same Error, Different Recovery: How Delivery Changes LLM Agent Behavior
cs.AI, cs.AR
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/BerriAI/litellm
Project page: https://openai.github.io
Terminology
Sources
- MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
- Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs
- On Randomness in Agentic Evals
- Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
- Bench2Robust: Scenario-Controlled Recovery for Tool-Using Agents
- The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models
- ARE: Scaling Up Agent Environments and Evaluations
- The Llama 3 Herd of Models
- ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents
- Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail
- CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios
- Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents
- ReIn: Conversational Error Recovery with Reasoning Inception
- Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents
- What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
- Qwen2.5 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents