arXiv AI
Jul 14
AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
MCP Error Messages Written for Developers Hurt the Most Capable Agents Most
Related stories
arXiv AI
Jun 6
A Taxonomy of Runtime Faults in Model Context Protocol Servers
arXiv:2606. 05339v1 Announce Type: cross Abstract: MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools and data sources via a standardized protocol.
arXiv AI
Aug 26
Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail
The study investigates why small language model agents tend to repeat a tool call that just failed. By recording the failed call and its error message in the transcript, the authors measure a negative corrective gain—agents are more likely to repeat the failed action, with a drop of about 1.03 nats per token. The problem is traced to the harness design rather than the model’s understanding of errors, and the authors show that replacing the verbatim call with a runtime-generated description of the failure can reduce this backfiring effect by 76%.
arXiv AI
Jun 30
From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes
arXiv:2606. 29073v1 Announce Type: cross Abstract: Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports.
arXiv AI
Sep 12
What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead
The study examines the composition of a random sample from the Model Context Protocol (MCP) registry, revealing that only 48.8% of the 400 sampled npm/stdio servers successfully complete an initialization handshake, compared to 66.7% for a hand‑curated frame. Among the servers that run, there are no fatal JSON Schema violations across 2,766 advertised tools, but optional safety annotations vary widely, with a 58.8% omission rate in the random draw versus 41.5% in the curated set. The authors also compare MCP tool descriptions to two benchmark corpora, finding minimal near‑duplication in real MCP tools (2.8%) and significant repetition in synthetic datasets (up to 85.6%).
arXiv Computation and Language
Sep 23
FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents
arXiv:2609.26048v1 Announce Type: cross Abstract: Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language i...
Hugging Face Trending Papers
Aug 4
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer and exhibit redundant exploration or looping, suggesting that some failures may be detectable before completion.
arXiv AI
Jul 13
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
arXiv:2607. 09510v1 Announce Type: cross Abstract: Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern.
arXiv Computation and Language
Aug 21
One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
arXiv:2608. 19741v1 Announce Type: new Abstract: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling.
arXiv AI
Aug 5
Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks
arXiv:2608. 03222v1 Announce Type: cross Abstract: Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates.
arXiv AI
Jul 24
DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers
arXiv:2607. 20531v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed over Model Context Protocol (MCP) servers, yet the benchmarks used to evaluate them score the final answer or a fixed "ground-truth" list of tools, both of which are fragile once the underlying data is live and stateful.
arXiv Computation and Language
Sep 23
Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation
arXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action....