Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

Ziyou Hu, Zhengliang Shi, Minghang Zhu, Haitao Li, Teng Sun, Pengjie Ren, Suzan Verberne, Zhaochun Ren · Oct 28, 2025 · Citations: 0

Automatic Metrics General Human Eval Pairwise Preference Tool Use
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Moderate trust

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

Best use

Primary benchmark and eval reference

What to verify

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

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

Abstract

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks, where evaluating correctness requires grounding beyond the model's internal knowledge. This limitation hinders them from reliably discriminating subtle quality differences, especially when external evidence is necessary. To address this, we introduce OpenRM, a tool-augmented long-form reward model that systematically judges open-ended responses by invoking external tools to gather relevant evidence. We train OpenRM with Group Relative Policy Optimization (GRPO) on over 27K synthesized pairwise examples generated through a controllable data synthesis framework. The training objective jointly supervises intermediate tool usage and final outcome accuracy, incentivizing our reward model to learn effective evidence-based judgment strategies. Extensive experiments on three newly-collected datasets and two widely-used benchmarks demonstrate that OpenRM substantially outperforms existing reward modeling approaches. As a further step, we integrate OpenRM into both inference-time response selection and training-time data selection. This yields consistent gains in downstream LLM alignment tasks, highlighting the potential of tool-augmented reward models for scaling reliable long-form evaluation.

Should You Rely On This Paper?

This paper has strong direct human-feedback and evaluation protocol signal and is suitable as a primary eval pipeline reference.

Best use

Primary benchmark and eval reference

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Usefulness score

77/100 • High

Use this as a primary source when designing or comparing eval protocols.

Human Feedback Signal

Detected

Evaluation Signal

Detected

Usefulness for eval research

High-confidence candidate

Extraction confidence 70%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

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

Pairwise Preference

Directly usable for protocol triage.

"Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference."

Evaluation Modes

strong

Human Eval, Automatic Metrics

Includes extracted eval setup.

"Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference."

Reported Metrics

strong

Accuracy

Useful for evaluation criteria comparison.

"The training objective jointly supervises intermediate tool usage and final outcome accuracy, incentivizing our reward model to learn effective evidence-based judgment strategies."

Human Feedback Details

  • Uses human feedback: Yes
  • Feedback types: Pairwise Preference
  • Rater population: Not reported
  • Unit of annotation: Pairwise
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Human Eval, Automatic Metrics
  • Agentic eval: Tool Use
  • Quality controls: Not reported
  • Evidence quality: Moderate
  • Use this page as: Primary benchmark and eval reference

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

accuracy

Research Brief

Metadata summary

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference.

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

Key Takeaways

  • Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference.
  • However, existing RMs struggle on knowledge-intensive and long-form tasks, where evaluating correctness requires grounding beyond the model's internal knowledge.
  • This limitation hinders them from reliably discriminating subtle quality differences, especially when external evidence is necessary.

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, Automatic metrics) 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.

Research Summary

Contribution Summary

  • Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference.
  • To address this, we introduce OpenRM, a tool-augmented long-form reward model that systematically judges open-ended responses by invoking external tools to gather relevant evidence.
  • Extensive experiments on three newly-collected datasets and two widely-used benchmarks demonstrate that OpenRM substantially outperforms existing reward modeling approaches.

Why It Matters For Eval

  • Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference.
  • To address this, we introduce OpenRM, a tool-augmented long-form reward model that systematically judges open-ended responses by invoking external tools to gather relevant evidence.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Pass: Evaluation mode is explicit

    Detected: Human Eval, Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.