Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

ToolTurns: Benchmarking LLM Agents in Multi-Turn Dialogue

Milad Gholami, Brendan King, Jeffrey Flanigan

Published

Nov 11, 2026

Citations

0

Trust level

Moderate

Usefulness score

69/100 (Medium)

Extraction confidence

65% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 11, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

General Human Eval Rubric Rating Simulation Env Tool Use

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The abstract does not clearly name benchmarks or metrics.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
69/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

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 language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests. We introduce ToolTurns, a benchmark of 2,620 problems spanning 1,827 tools and 11,004 API endpoints across 47 categories. Each dialogue begins with an intentionally underspecified request and continues through two context-dependent follow-ups, testing clarification, tool use, and retention of conversational context. We also introduce an open-source user simulator that reveals withheld context through dialogue and generates follow-up requests, with a checker--fixer pipeline for improving its turns. Across nine language models, the best agent resolves 69.6% of individual requests but completes only 39.8% of full dialogues. Under this evaluation protocol, every evaluated model receives lower success scores on follow-up requests than on the initial request, and dialogue-quality rubric scores and task success can rank models very differently. Paired turn-level evaluation shows that the checker--fixer reduces detected dialogue defects, and blind human evaluation favors the revised turns. ToolTurns provides a testbed for evaluating whether agents sustain task success across multi-turn dialogue with tools.

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

strong

Rubric Rating

Directly usable for protocol triage.

"Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests."

Evaluation Modes

strong

Human Eval, Simulation Env

Includes extracted eval setup.

"Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Rubric Rating
Rater population
Not reported
Unit of annotation
Multi Dim Rubric
Expertise required
General
Evaluation details
Evaluation modes
Human Eval, Simulation Env
Agentic eval
Tool Use
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests.

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

Key takeaways

  • Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests.
  • We introduce ToolTurns, a benchmark of 2,620 problems spanning 1,827 tools and 11,004 API endpoints across 47 categories.
  • Each dialogue begins with an intentionally underspecified request and continues through two context-dependent follow-ups, testing clarification, tool use, and retention of conversational context.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Human evaluation, Tool-use evaluation) 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

Rubric rating evaluation

Contribution summary

  • Tool-using language models are increasingly deployed in conversational settings, yet most large-scale tool-use benchmarks focus on isolated requests.
  • We introduce ToolTurns, a benchmark of 2,620 problems spanning 1,827 tools and 11,004 API endpoints across 47 categories.

Why it matters for eval

  • Under this evaluation protocol, every evaluated model receives lower success scores on follow-up requests than on the initial request, and dialogue-quality rubric scores and task success can rank models very differently.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Rubric Rating

  • Evaluation mode is explicit

    Detected: Human Eval, Simulation Env

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.