Measuring and Reducing Unusable Replies of LLM Agents

cs.CL, cs.AI, cs.HC

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 17 pages, 4 figures, 12 tables

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

Sources

• Challenges in Human-Agent Communication
• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models
• Evaluating Large Language Models Trained on Code
• Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
• Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models
• The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
• Language Models Are "Insecure" Reporters
• Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
• MemGPT: Towards LLMs as Operating Systems
• How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
• The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering