pith. sign in

arxiv: 2502.19328 · v1 · pith:AIJBOCS3new · submitted 2025-02-26 · 💻 cs.CL · cs.AI

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

classification 💻 cs.CL cs.AI
keywords rewardmodelssignalsverifiablecorrectnesshumanreliablerewardagent
0
0 comments X
read the original abstract

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown strong potential in training LLMs. In this paper, we propose agentic reward modeling, a reward system that combines reward models with verifiable correctness signals from different aspects to provide reliable rewards. We empirically implement a reward agent, named RewardAgent, that combines human preference rewards with two verifiable signals: factuality and instruction following, to provide more reliable rewards. We conduct comprehensive experiments on existing reward model benchmarks and inference time best-of-n searches on real-world downstream tasks. RewardAgent significantly outperforms vanilla reward models, demonstrating its effectiveness. We further construct training preference pairs using RewardAgent and train an LLM with the DPO objective, achieving superior performance on various NLP benchmarks compared to conventional reward models. Our codes are publicly released to facilitate further research (https://github.com/THU-KEG/Agentic-Reward-Modeling).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. StoryAlign: Evaluating and Training Reward Models for Story Generation

    cs.CL 2026-05 unverdicted novelty 7.0

    StoryReward, trained on a new 100k story preference dataset, sets state-of-the-art performance on the introduced StoryRMB benchmark for aligning LLM stories with human preferences.

  2. Visual-ERM: Reward Modeling for Visual Equivalence

    cs.CV 2026-03 unverdicted novelty 7.0

    Visual-ERM is a new multimodal reward model that supplies fine-grained visual feedback for training vision-language models on chart-to-code, table, and SVG tasks, yielding measurable gains over prior rewards.

  3. SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning

    cs.AI 2026-04 unverdicted novelty 4.0

    SPREG detects logical failures in LLM long-chain reasoning through real-time entropy spikes and performs structured plan repairs using historical distributions, reporting a 20% absolute accuracy gain on AIME25.

  4. From System 1 to System 2: A Survey of Reasoning Large Language Models

    cs.AI 2025-02 accept novelty 3.0

    The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.

  5. Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

    cs.AI 2025-03 unverdicted novelty 2.0

    This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.