aiqbench analysis
EAVer introduces an agentic framework that unifies long-form factuality verification into a single policy, optimizing the balance between direct LLM reasoning and external search. By grouping related claims and reusing evidence, the system significantly reduces redundant tool calls while improving accuracy on standard benchmarks compared to static pipelines. This approach demonstrates how agent-level orchestration can enhance efficiency and reliability in automated verification workflows without relying on post-hoc rationales.
EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy
arXiv:2609.22223v1 Announce Type: new 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.
Authors:Kening Zheng, Aoying Zheng, Zhigang Chang, Yazhi Guo, Miaotian Guo, Qingwei Zong, Xianhai Xie, Weiqiang Jin, Chengze Li, Hanrong Zhang, Jie Yang, Wei-Chieh Huang, Lingzhe Zhang, Liancheng Fang, Xin Zou, Hanqian Li, Jiahao Huo, Yibo Yan, Zizhuang Deng, Lei Miao, Wei Guo, Haihong Tang, Bo Zheng, Philip S. Yu
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.
Computation and Language (cs.CL); Machine Learning (cs.LG)
arXiv:2609.22223 [cs.CL]
(or arXiv:2609.22223v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.22223 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 283 words
Related coverage
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
Lock-In Risk Needs More Researchers; Here's Where to Start
LessWrong · Jun 17, 2026