Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Repairs for Whom? Evaluator-Executor Mismatch in Selecting Repairs for Failed LLM Agents

Yijun Liao, Fanwei Liang

Published

Oct 28, 2026

Citations

0

Trust level

Low

Usefulness score

2/100 (Low)

Extraction confidence

40% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 28, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Simulation Env

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
2/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

When an LLM agent fails, repair methods choose which action to replace and what to put in its place. They often score candidate repairs with greedy replay, a stronger model, an environment oracle, or a judge that reads the failed log. We ask whether these evaluators pick repairs that help the agent that will actually execute them. Holding failed trajectories and candidate single-step repairs fixed, we label every candidate with independent rollouts of the deployed policy and measure how much deployment value each evaluator's choice loses. On failures not screened for repair value, pre-specified tests show that greedy replay loses 0.08-0.13 in expected net success gain in ALFWorld and 0.06-0.13 in net reward in WebShop, relative to selection with the deployed agent's own rollouts. At an equal rollout budget, selecting repairs for Qwen2.5-7B with Qwen2.5-14B rollouts loses 0.25 in ALFWorld and 0.07 in WebShop, twenty 14B rollouts per candidate are worth no more than two of the 7B agent's own, and fresh rollouts confirm that the two models prefer opposite repairs on selected disagreement cases. Between similar-sized models from different families, the losses appear in both directions in both environments (0.07-0.17). The scoring executor also changes repair-location labels and method rankings. Repairs should be verified with the executor that will run them, and repair labels should name their executor.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"When an LLM agent fails, repair methods choose which action to replace and what to put in its place."

Evaluation Modes

partial

Simulation Env

Includes extracted eval setup.

"When an LLM agent fails, repair methods choose which action to replace and what to put in its place."

Quality Controls

missing

Not reported

No explicit QC controls found.

"When an LLM agent fails, repair methods choose which action to replace and what to put in its place."

Benchmarks / Datasets

partial

ALFWorld, WebShop

Useful for quick benchmark comparison.

"On failures not screened for repair value, pre-specified tests show that greedy replay loses 0.08-0.13 in expected net success gain in ALFWorld and 0.06-0.13 in net reward in WebShop, relative to selection with the deployed agent's own rollouts."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"When an LLM agent fails, repair methods choose which action to replace and what to put in its place."

Benchmarks and datasets

ALFWorldWebShop

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Ranking (inferred)
Expertise required
General
Evaluation details
Evaluation modes
Simulation Env
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

When an LLM agent fails, repair methods choose which action to replace and what to put in its place.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • When an LLM agent fails, repair methods choose which action to replace and what to put in its place.
  • They often score candidate repairs with greedy replay, a stronger model, an environment oracle, or a judge that reads the failed log.
  • We ask whether these evaluators pick repairs that help the agent that will actually execute them.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Simulation environment) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • When an LLM agent fails, repair methods choose which action to replace and what to put in its place.
  • They often score candidate repairs with greedy replay, a stronger model, an environment oracle, or a judge that reads the failed log.
  • We ask whether these evaluators pick repairs that help the agent that will actually execute them.

Why it matters for eval

  • When an LLM agent fails, repair methods choose which action to replace and what to put in its place.
  • They often score candidate repairs with greedy replay, a stronger model, an environment oracle, or a judge that reads the failed log.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Simulation Env

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: ALFWorld, WebShop

  • Metric reporting is present

    No metric terms extracted.