Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Not Every User Says It All: Training Tool-Using Agents Beyond Ideal Simulated Users

Han Bao, Zheyuan Zhang, Kaiwen Shi, Yanfang Ye

Published

Oct 16, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

25% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 16, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

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

Background context only.

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
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
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

Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker. We construct weak users by masking sentences of a simulated user's replies, holding the task and the user's knowledge fixed, and cross-evaluate agents trained with strong and weak users on tau2-bench and ToolWOZ. Weak users lower the success of every policy, and training with them does not help: no policy trained with weak users, through fixed masks, mixtures or a curriculum, serves weak users better than the strong-trained policy beyond run-to-run noise, and prompting the agent to ask more does not help either. We propose StaGPO (State-Grouped Policy Optimization): the agent writes what the task needs, what is missing and how it is being filled, and GRPO uses this state to compare turns of different rollouts that reach the same situation, assigning step-level credit. Within the standard recipe of a small SFT cold start followed by RL, StaGPO makes weak-user training useful: on ToolWOZ, the Qwen3.5-2B policy trained with weak users reaches 76.8% with weak users, the highest of any Qwen3.5-2B policy we trained, 4.8 points above GRPO and 2.8 above the strongest baseline; it is also 5.4 points above GRPO with strong users, and generalises to an unseen mask rate; trained with strong users instead, it serves weak users at least as well as GRPO trained with weak users. On tau2-bench it scores highest with weak users for both models, by a small margin for Qwen3.5-4B.

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.

"Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker."

Benchmarks / Datasets

partial

Tau2 Bench

Useful for quick benchmark comparison.

"We construct weak users by masking sentences of a simulated user's replies, holding the task and the user's knowledge fixed, and cross-evaluate agents trained with strong and weak users on tau2-bench and ToolWOZ."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker."

Benchmarks and datasets

Tau2-Bench

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
Trajectory (inferred)
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker.

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

Key takeaways

  • Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker.
  • We construct weak users by masking sentences of a simulated user's replies, holding the task and the user's knowledge fixed, and cross-evaluate agents trained with strong and weak users on tau2-bench and ToolWOZ.
  • Weak users lower the success of every policy, and training with them does not help: no policy trained with weak users, through fixed masks, mixtures or a curriculum, serves weak users better than the strong-trained policy beyond run-to-run noise, and prompting the agent to ask more does not help either.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • 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

  • Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker.
  • We construct weak users by masking sentences of a simulated user's replies, holding the task and the user's knowledge fixed, and cross-evaluate agents trained with strong and weak users on tau2-bench and ToolWOZ.
  • We propose StaGPO (State-Grouped Policy Optimization): the agent writes what the task needs, what is missing and how it is being filled, and GRPO uses this state to compare turns of different rollouts that reach the same situation,…

Why it matters for eval

  • Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker.
  • We propose StaGPO (State-Grouped Policy Optimization): the agent writes what the task needs, what is missing and how it is being filled, and GRPO uses this state to compare turns of different rollouts that reach the same situation,…

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: Tau2-Bench

  • Metric reporting is present

    No metric terms extracted.