Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Harness-G: Graph-Structured Interface Boosts Search Agent Performance

AI By Crimson AI Hugging Face Papers 2 August 2026 · 00:00 28 views
Share: X Telegram

A new framework from Hugging Face researchers, Harness-G, replaces free-form query generation in RL search agents with a finite menu of graph-based actions, mitigating retrieval-equivalence collapse and achieving state-of-the-art F1 scores on six QA benchmarks.

Harness-G: Graph-Structured Interface Boosts Search Agent Performance

Key points

Reinforcement learning (RL) search agents typically generate free-form natural-language queries to retrieve evidence, but researchers at Hugging Face have identified a critical flaw in this approach: retrieval-equivalence collapse. During training, agents often produce diverse query strings that lead to nearly identical evidence sets, leaving little contrast for optimization and reducing the effectiveness of group-relative credit assignment.

To address this, the team introduces Harness-G, a graph-structured retrieval framework that redesigns the policy-environment interface. Instead of generating free-form queries, the policy selects from a finite menu of typed, verifiable actions—such as choosing an evidence sentence or entity, or deciding to answer. The environment constructs the menu, tracks retrieval state, and validates and executes each choice, reducing linguistic aliasing and making alternatives directly comparable.

Building on this interface, the authors propose Structured Non-myopic Credit (SNC), which uses a frozen answer scorer to compare the selected action with its alternatives and assigns downstream gains to earlier actions that enabled them. This provides denser, more structured credit signals for training.

Across six question-answering benchmarks, Harness-G achieves the highest average F1 at both evaluated model scales (1.5B and 3B), outperforming the strongest baseline, Graph-R1, by 10.74 points at 1.5B and 3.98 points at 3B. The work highlights the importance of properly formulating retrieval at the policy-environment interface for effective RL training.

Model ScaleHarness-G (Avg F1)Graph-R1 (Avg F1)Improvement
1.5B+10.74
3B+3.98
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1