Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- MemGPT: Towards LLMs as Operating Systems
- Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
- Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
- Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback
- ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
- Why Do Multi-Agent LLM Systems Fail?
- Locating Hidden Failures Makes Long-Horizon Agents More Reliable
- Correlated Failures of AI Approval Monitors
- Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks
- Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction
- Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents
- UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents
- TRAIL: Trace Reasoning and Agentic Issue Localization
- Quantifying Overclaiming Propensity in Frontier LLM Agents
- Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents
- When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems
- Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
- READY or Not: Reliable Enterprise Agent Deployment
- Looks Fine to Me: Understanding Oversight in Agentic Interactions
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