Skip to content
← Back to explorer

HFEPX Hub

CS.CL + Web Browsing Papers

Updated from current HFEPX corpus (Feb 27, 2026). 12 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequently cited benchmark: APPS. 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: 12 Last published: Feb 25, 2026 Global RSS Tag RSS
Cs.CLWeb Browsing

Research Narrative

Grounded narrative Model: deterministic-grounded Source: persisted

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 12 papers for CS.CL + Web Browsing Papers. Dominant protocol signals include automatic metrics, simulation environments, human evaluation, with frequent benchmark focus on APPS, Memoryarena and metric focus on accuracy, task success. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Why This Matters For Eval Research

Protocol Takeaways

Benchmark Interpretation

  • APPS appears in 8.3% of hub papers (1/12); use this cohort for benchmark-matched comparisons.
  • Memoryarena appears in 8.3% of hub papers (1/12); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 25% of hub papers (3/12); compare with a secondary metric before ranking methods.
  • task success is reported in 16.7% of hub papers (2/12); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Close gap on Papers with explicit human feedback. Coverage is a replication risk (25% vs 45% target).
  • Close gap on Papers reporting quality controls. Coverage is a replication risk (0% vs 30% target).
  • Tighten coverage on Papers naming benchmarks/datasets. Coverage is usable but incomplete (33.3% vs 35% target).
  • Maintain strength on Papers naming evaluation metrics. Coverage is strong (66.7% vs 35% target).
  • Close gap on Papers with known rater population. Coverage is a replication risk (8.3% vs 35% target).
  • Close gap on Papers with known annotation unit. Coverage is a replication risk (8.3% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (25% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (0% vs 30% target).

Papers naming benchmarks/datasets

Coverage is usable but incomplete (33.3% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (66.7% vs 35% target).

Papers with known rater population

Coverage is a replication risk (8.3% vs 35% target).

Papers with known annotation unit

Coverage is a replication risk (8.3% 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 here for detailed protocol reporting, including rater and quality-control evidence.

  2. 2. A Benchmark for Deep Information Synthesis

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  3. 3. Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  4. 4. Modeling Distinct Human Interaction in Web Agents

    Adds automatic metrics with pairwise preferences for broader coverage within this hub.

  5. 5. MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks

    Adds simulation environments with pairwise preferences for broader coverage within this hub.

  6. 6. The Automatic Verification of Image-Text Claims (AVerImaTeC) Shared Task

    Adds automatic metrics for broader coverage within this hub.

  7. 7. UI-Venus-1.5 Technical Report

    Adds simulation environments for broader coverage within this hub.

  8. 8. INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection

    Adds automatic metrics for broader coverage within this hub.

Known Limitations

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.3% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.

Research Utility Links

human_eval vs automatic_metrics

both=1, left_only=0, right_only=8

1 papers use both Human Eval and Automatic Metrics.

automatic_metrics vs simulation_env

both=0, left_only=9, right_only=3

0 papers use both Automatic Metrics and Simulation Env.

simulation_env vs human_eval

both=0, left_only=3, right_only=1

0 papers use both Simulation Env and Human Eval.

Benchmark Brief

APPS

Coverage: 1 papers (8.3%)

1 papers (8.3%) mention APPS.

Examples: UI-Venus-1.5 Technical Report

Benchmark Brief

Memoryarena

Coverage: 1 papers (8.3%)

1 papers (8.3%) mention Memoryarena.

Examples: MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks

Benchmark Brief

Retrieval

Coverage: 1 papers (8.3%)

1 papers (8.3%) mention Retrieval.

Examples: A Benchmark for Deep Information Synthesis

Metric Brief

accuracy

Coverage: 3 papers (25%)

3 papers (25%) mention accuracy.

Examples: GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL , Modeling Distinct Human Interaction in Web Agents , The Automatic Verification of Image-Text Claims (AVerImaTeC) Shared Task

Metric Brief

task success

Coverage: 2 papers (16.7%)

2 papers (16.7%) mention task success.

Examples: GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL , Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Metric Brief

f1

Coverage: 1 papers (8.3%)

1 papers (8.3%) mention f1.

Examples: A Benchmark for Deep Information Synthesis

Most Cited In This Hub

Fast path to methods with the strongest citation traction in this scope.

Papers: GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL , A Benchmark for Deep Information Synthesis , Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Most Recent

Fast path to latest protocol changes and newly published evaluation setups.

Papers: GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL , A Benchmark for Deep Information Synthesis , Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Best Protocol Detail

Papers with explicit rater/unit metadata and quality-control signals for reproducibility.

Papers: GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL , A Benchmark for Deep Information Synthesis , Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Top Papers

Related Hubs