Skip to content
← Back to explorer

HFEPX Hub

Tool Use Or Web Browsing Papers

Updated from current HFEPX corpus (Feb 27, 2026). 33 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: BrowseComp. Common metric signal: accuracy. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Feb 25, 2026.

Papers: 33 Last published: Feb 25, 2026 Global RSS Tag RSS
Tool UseWeb Browsing

Research Narrative

Grounded narrative Model: deterministic-grounded

Updated from current HFEPX corpus (Feb 27, 2026). This page covers 33 papers centered on Tool Use Or Web Browsing Papers. Common evaluation modes include Automatic Metrics, Simulation Env, with benchmark emphasis on BrowseComp, MMLU. Metric concentration includes accuracy, cost, and the agentic footprint highlights Web Browsing, Tool Use. Use the anchored takeaways below to compare protocol choices, quality-control patterns, and evidence depth before allocating new eval budget.

Why This Matters For Eval Research

Protocol Takeaways

Benchmark Interpretation

  • BrowseComp appears as a recurring benchmark anchor in this page.
  • 2 papers (6.1%) mention BrowseComp.
  • Most common evaluation modes: Simulation Env, Automatic Metrics.

Metric Interpretation

  • accuracy is a common reported metric and should be paired with protocol context before ranking methods.
  • 4 papers (12.1%) mention accuracy.
  • Most common evaluation modes: Automatic Metrics, Simulation Env.

Researcher Checklist

  • Papers with explicit human feedback: Coverage is a replication risk (24.2% vs 45% target).
  • Papers reporting quality controls: Coverage is a replication risk (3% vs 30% target).
  • Papers naming benchmarks/datasets: Coverage is strong (36.4% vs 35% target).
  • Papers naming evaluation metrics: Coverage is strong (51.5% vs 35% target).
  • Papers with known rater population: Coverage is a replication risk (15.2% vs 35% target).
  • Papers with known annotation unit: Coverage is a replication risk (15.2% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (24.2% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (3% vs 30% target).

Papers naming benchmarks/datasets

Coverage is strong (36.4% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (51.5% vs 35% target).

Papers with known rater population

Coverage is a replication risk (15.2% vs 35% target).

Papers with known annotation unit

Coverage is a replication risk (15.2% vs 35% target).

Suggested Reading Order

  1. 1. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

    Start with this anchor paper for scope and protocol framing. Covers Automatic Metrics.

  2. 2. Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference

    Covers Automatic Metrics.

  3. 3. Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids

    Covers Simulation Env.

  4. 4. A Benchmark for Deep Information Synthesis

    Covers Human Eval, Automatic Metrics.

  5. 5. SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

    Covers Simulation Env.

  6. 6. PyVision-RL: Forging Open Agentic Vision Models via RL

    Covers Automatic Metrics.

  7. 7. Onboard-Targeted Segmentation of Straylight in Space Camera Sensors

    Covers Automatic Metrics.

  8. 8. Contextual Safety Reasoning and Grounding for Open-World Robots

    Covers Simulation Env.

Known Limitations

  • Narrative synthesis is grounded in metadata and abstracts only; full-paper method details may be missing.
  • Extraction fields are conservative and can under-report implicit protocol details.
  • Cross-page comparisons should control for benchmark and metric mismatch.

Research Utility Links

human_eval vs automatic_metrics

both=1, left_only=0, right_only=21

1 papers use both Human Eval and Automatic Metrics.

automatic_metrics vs simulation_env

both=1, left_only=21, right_only=11

1 papers use both Automatic Metrics and Simulation Env.

simulation_env vs human_eval

both=0, left_only=12, right_only=1

0 papers use both Simulation Env and Human Eval.

Top Papers

Related Hubs