1 citations · 2 across the 13 of their papers we have counts for
18 papers
Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads
Jingjie Ning, Xueqi Li, Yibo Kong
Evaluation budgets in agentic retrieval-augmented generation span questions, search trajectories, and repeated answers. We measure allocation precision, reading efficiency, and cos…
Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts
Jingjie Ning, Xueqi Li, Yibo Kong +1
Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while varying description, matched…
Rules to Tools: Executable Checks for LLM Agents in Scientific Computing
Jingjie Ning, Guojiang Zhao, Chen Xu +4
Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to Tools (R2T) supplies prepar…
The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents
Xueqi Li, Jingjie Ning, Yibo Kong
An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability when a default-aligned whole p…
ControlScope: Workflow Revision and Reliability in LLM Agents
Jingjie Ning, Xueqi Li, Yibo Kong +1
How much of a running workflow should a language model agent revise? ControlScope compares continuing generated code, editing the next tool call's data arguments, and replacing the…
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
Jingjie Ning, Xueqi Li, Yibo Kong +1
AI research agents must predict the effects of computational changes after budgeted experiments. WhatWorkedBench evaluates this experimental understanding through a delivered respo…
Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents
Jingjie Ning, Shanshan Zhong, Xiaochuan Li +1
AI research agents combine public information and experimental feedback to produce measurable results. The Discovery Certification Protocol (DCP) turns an outcome claim into an exe…
Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA
Jingjie Ning, Xueqi Li
A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval policy, evidence depth, rendering,…
The Implementation Lottery: Auditing Idea Reliability in Automated Research
Jingjie Ning, Shanshan Zhong, Xiaochuan Li +2
Automated research agents use program scores to judge ideas. We call variation in this evidence across implementations the implementation lottery. We introduce an Idea Reliability…
Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer
Jingjie Ning, Xiaochuan Li, Shanshan Zhong +2
Auto Research uses language-model agents to propose, implement, and evaluate machine-learning changes in a closed loop, but is usually judged by its terminal pipeline. A terminal s…
Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements
Jingjie Ning, Xiaochuan Li, Ji Zeng +2
Closed-loop Auto Research extends automated machine learning from fixed-dataset fitting to changing the research workflow, with language-model agents editing representations and mo…
Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
Sidhaarth Murali, João Coelho, Jingjie Ning +3
Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory) or breadth (i.e., more parallel rollouts). Here we focus on breadth scal…
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
Jingjie Ning, Xiaochuan Li, Ji Zeng +2
We study auto research as a closed empirical loop driven by external measurement. Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, an…
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
Shanshan Zhong, Yi Lu, Jingjie Ning +7
Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically…
Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
Jingjie Ning, Xueqi Li, Chengyu Yu
Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine error correction. We q…
Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests
Jingjie Ning, João Coelho, Yibo Kong +5
LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understanding of how agentic search sessions un…
Less LLM, More Documents: Searching for Improved RAG
Jingjie Ning, Yibo Kong, Yunfan Long +1
Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators often improves accuracy, it also increases inference and…
DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
João Coelho, Jingjie Ning, Jingyuan He +8
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most…