Read original ↗
paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing to inform the model about the goodness of intermediate actions. Dense supervision methods aim to solve this problem by scoring intermediate steps, from intrinsic confidence to self-distillation and embedding similarities. However, it is common practice to evaluate them by measuring the downstream performance of a training pipeline that integrates them. This is expensive, conflates supervision quality

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

Has model

modelAgentCore-8B

Covers

newsAlibaba's model never trained as an agent — and improved agent performance across seven benchmarks

Covers (incoming)

newsCompetence Gate: gating tool-use on a small model's internal confidence signal instead of its verbalised one — Qwen3.5-4B, open weights [P]

Implements (incoming)

repoNirDiamant/GenAI_Agentsreporoboflow/supervisionrepoThysrael/HorizonrepoUnity-Technologies/ml-agentsrepodatawhalechina/hello-agents

Related across the graph

reporoboflow/supervisionnewsCompetence Gate: gating tool-use on a small model's internal confidence signal instead of its verbalised one — Qwen3.5-4B, open weights [P]repodatawhalechina/hello-agentsrepoThysrael/HorizonnewsAlibaba's model never trained as an agent — and improved agent performance across seven benchmarksrepoUnity-Technologies/ml-agentsmodelAgentCore-8BrepoNirDiamant/GenAI_Agents

Topics

cs.AI