arXiv AI

Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents

arXiv AI
Oct 15

JevGPT: Thinking Fast and Slow in Autonomous Research

JevGPT is a dual‑system architecture for autonomous research that combines fast evidence processing (System One) with deliberative research planning (System Two). System One quickly locates and evaluates relevant passages, while System Two sets evidence objectives and integrates findings into subsequent research steps. Experiments on question answering and document ranking demonstrate that JevGPT outperforms comparable agents, achieving faster completion, lower cost, and broader source coverage.

By Yasheng Sun, Yanning Dai, Yimeng Chen, Nanbo Li, Firas Laakom, Yifan Xu, Piotr Pi\k{e}kos, Mateusz Ostaszewski, Wenyi Wang, Cheng Luo, Yuhui Wang, J\"urgen Schmidhuber
arXiv AI
Oct 5

Counterfactual Evidence Audits Predict LLM-Agent Susceptibility to Ranked Context

The paper introduces a counterfactual evidence audit to assess how large language model agents respond to different sets of documents. By exposing agents to two mirrored sets of five documents and measuring changes in six downstream decisions, the authors predict how the agents will behave when presented with a full 45‑document context. Across multiple open‑weight model families and tasks, the five‑document audit accurately forecasts full‑context effects, reducing prediction error by 62% and correctly identifying the direction of most material effects.

By Rana Muhammad Usman
arXiv AI
Oct 19

Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research

Optimist Deep Research is an open‑source agent that conducts literature research as an iterative, state‑centric process. It breaks a research question into a tree of subquestions, uses search intents to query multiple scholarly databases, and merges results into a provenance‑preserving document registry. The agent iteratively expands the registry via citation snowballing, evaluates evidence, and refines the research plan through a critic that can add, split, rephrase, deprioritize, or close subquestions, ultimately producing a report with every citation linked to a retrieved document.

By Gihan Panapitiya
arXiv AI
Oct 28

When Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths

The paper introduces Contrastive Evidence Paths (CEP), a method that scores search candidates by their strongest individual paths on a query‑conditioned document graph and calibrates these scores against a background visitation distribution to reduce structural bias. Building on CEP, Structured Corpus Interaction (SCI) organizes candidates and paths into a structured map, allowing agents to verify sources and expand from anchor documents. Experiments on BrowseComp‑Plus and TREC‑COVID demonstrate that SCI achieves state‑of‑the‑art answer accuracy and nDCG@10 while cutting tool calls and generation costs by over 50% and 40%, respectively.

By Junchen Li, Liang Xu, Rongzheng Wang, Qizhi Chen, Junhao Wen, Shuang Liang
arXiv Computation and Language
Sep 15

CITECHOICE: A Causal Audit of How Document Presentation Redistributes Citation Credit in Agentic Search

CITECHOICE is a causal audit that examines how the presentation of documents in an agentic search engine redistributes citation credit. Using 129 everyday‑query transcripts, the study compares structured versus prose renderings of the same source while keeping all other transcript elements fixed. The results show that structured rendering increases the target’s citation count by about half a citation per answer without adding total citations or diminishing competitors’ credit, while also revealing that rank position has a larger effect on citation rates than presentation order alone.

By Sriram Selvam, Anneswa Ghosh
arXiv Computation and Language
Nov 5

Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis

The study investigates how cognitive biases influence large language model (LLM) agents that use search. By controlling search conditions across 10 models and 1,000 synthetic search scenarios, the authors examine how the order of evidence, prior work records, and initial hypotheses affect retrieval, document opening, and final answers. Findings indicate that initial evidence order during active search has a stronger impact on outcomes than when all evidence is presented at once, and that dead‑end histories reduce strategy switching beyond what context length alone would explain.

By Yanru Xiao, Yingwei Yu
arXiv Computation and Language
Oct 12

SEEDS: Preview-Guided Evidence Admission for Search Agents

The paper introduces SEEDS, a preview-guided evidence admission framework that allows search agents to selectively admit retrieved documents into their reasoning process. SEEDS exposes lightweight previews of candidates and lets the agent decide which and how many to fully inspect based on its current reasoning state, enabling arbitrary subset selection rather than fixed or rank-based policies. Experiments on nine knowledge-intensive QA benchmarks show that SEEDS improves search effectiveness and reduces full-evidence consumption compared to traditional retrieval prefixes.

By Jiajin Liu, Chenxi Xu, Dongzhe Fan, Yuanfu Sun, Qiaoyu Tan