arXiv AI August 26, 2026 By Esmail Gumaan

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%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 30

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

arXiv:2607. 26117v1 Announce Type: cross Abstract: Self-repair - returning a failed program to the model together with its test output and asking for a correction - is a standard component of code agents, and is almost always evaluated against a baseline that does not retry at all.

By Yuvraj Verma

agents

Hugging Face Trending Papers

Jun 24

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.

llms benchmarks

arXiv AI

Jun 9

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

arXiv:2606. 07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction.

By Sanjay Kariyappa, G. Edward Suh

llms agents benchmarks

arXiv AI

Aug 3

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.

By Xiaonan Xu, Wenjing Wu

llms agents

arXiv Machine Learning

Jun 25

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

arXiv:2606. 25449v1 Announce Type: cross Abstract: A language model's memory can be worse than having no memory at all.

By Alex Kwon

llms benchmarks

arXiv AI

Jun 2

Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems

arXiv:2606. 01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery.

By Rahul Suresh Babu, Adarsh Agrawal

llms agents benchmarks

One email a morning, machine-written

Related stories

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems