Skip to content

EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy

Sep 2026 · 0 citations · 22 references
Computer Science

TL;DR

This work introduces EAVer, an End-to-end Agentic Verifier that learns to control the complete response-level verification workflow as a unified policy, and construct 794 bidirectional same-trajectory preference pairs that keep claim grouping, search, and evidence fixed, enabling decision-focused Direct Preference Optimization over factuality-decision tokens.

Abstract

Long-form factuality verification is commonly implemented as a static decompose-search-verify pipeline, with separately prompted modules processing claims and invoking external search. Treating claims independently makes LLM and search calls scale with claim count and causes repeated searches for overlapping evidence about related claims. We introduce EAVer, an End-to-end Agentic Verifier that learns to control the complete response-level verification workflow as a unified policy. EAVer groups semantically related claims, routes each group to direct verification or targeted search based on confidence, and keeps evidence returned by search in compact in-context memos for cross-claim reuse. To train this policy, we develop a privileged-teacher synthesis pipeline that converts gold claim annotations into executable multi-turn tool-interaction trajectories with live search rather than post-hoc rationales. Structural, label-alignment, tool-use, search-budget, and leakage checks yield 1,447 quality-controlled trajectories. We further construct 794 bidirectional same-trajectory preference pairs that keep claim grouping, search, and evidence fixed, enabling decision-focused Direct Preference Optimization (DPO) over factuality-decision tokens. The results with Qwen3-8B show that EAVer outperforms the strongest search-based baseline on each benchmark by 2.88 Macro-F1 points on VeriFastScore and 4.73 points on the out-of-distribution FaStFact-Bench, while using about 80% fewer searches than the most search-efficient baseline. Moreover, EAVer consistently improves performance across models ranging from 4B to 32B parameters, demonstrating its strong generalizability.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents

Long-horizon tool-using AI agents create subgoals, replan, delegate work, and compose sibling results. Per-tool permission checks cannot establish that a changing goal graph remains within the principal-approved task. We address this authorization gap in a finite structured domain with one principal and one authorizati...

Gen-Liang Zhu, Chu Wang · 1 citation
Book Open access Oct 2026

Formal Runtime Verification for Tool-Using LLM Agents: An Offline Same-Benchmark Study on AgentDojo and STAC

Results show that formal temporal monitoring adds value exactly when the trace exposes trustworthy history, and quantify how far current benchmarks are from that point and propose a twelve-field enforcement-ready trace schema.

N. Kekatos, Stylianos Basagiannis, Marinelio Chintri et al. · 2 citations
#artificial intelligence Review Sep 2026

LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents

Test-time scaling improves software engineering agents by generating multiple candidate trajectories and selecting the best one. Verifying and selecting among these long interactions can consume as many tokens as generation itself. Existing hybrid workflows first apply an LLM-based execution-free (EF) verifier to filte...

Yu-Ning Han, Yangchenchen Jin, Tyler Jandreau et al. · 0 citations
#software testing Preprint Sep 2026

From Approval to Execution: Reconstruction-Aware Repair Analysis for LLM-Agent Software

A reconstruction-stable authorization (ReSA) is formulated over representation transitions, sink dependencies, consumed versions, and grant scope and implemented in APAS-Finder and freeze predictions before an independent sink oracle observes execution.

Jun-Chi Zhu, Zhen-Guang Liu, Shao-Jing Fan et al. · 0 citations
#artificial intelligence Preprint Oct 2026

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened with a fixed base model, without access to reference answers or grading rubrics at test time. Repeated sampling yields multiple rollouts th...

Caiqi Zhang, Ru-Jun Han, Zifeng Wang et al. · 1 citation

Related blog posts

MIT News · Artificial Intelligence Aug 27, 2026

Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.