arXiv subjects

Xinran Zhao

Publications and source records attributed to Xinran Zhao.

At least 19 recordsLinked to original sources

arXiv2026

3DCodeEdit: Benchmarking Instruction-Guided 3D Program Editing

Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such edits require understanding what a program builds and foreseeing how a change reshapes it, yet prior benchmarks mostly evaluate generation or simple edits against a reference. In this paper, we introduce 3DCodeEdit, a benchmark of 2,592 instruction-guided editing tasks over 108 Blender programs that construct objects entirely in code. Its edits range from parameter to structural changes, style redesign, and scene composition, and are judged from renders against human-reviewed checklists. Across 17 models, the average success rate is only 37%, and even the strongest models complete fewer than 60% of structural and style edits. As models become more capable, their failures shift to geometric foresight, where the code runs but builds the wrong shape. We therefore study whether multi-turn feedback can compensate for this missing foresight. Feedback from a separate reviewer model that describes how the renders differ from the request helps most, more than maximum reasoning effort or an agent harness, and can let a 27B model surpass the single-shot rate of a 2.8T-parameter model.

cs.CL↗

arXiv2026

Knowing When to Stop: The Evidence-Action Gap in Coding Agents

Coding agents are trained to complete tasks, and they keep trying even when the environment makes completion impossible. The evidence that only outside help can restore progress usually appears within a few steps, yet agents rarely act on it: they over-persist, attempt undesired workarounds, and claim success the record does not support -- a phenomenon we call evidence-action gap. To measure it, we introduce ImpasseBench, which injects twelve realistic environment blockers into otherwise solvable repair tasks and marks, in each trajectory, the step at which the collected evidence becomes sufficient. Scoring actions relative to that step separates appropriate effort from over-persistence and premature handoff. Across eight frontier models and 19,371 trajectories, we find that nearly every run that needs outside help collects sufficient evidence, yet a third still exhaust their budget, and every unsafe request we detect comes after that point. Fortunately, an escalation tool, or an external monitor for models that ignore the tool, already guards against much of this behavior: the tool cuts budget exhaustion from 34.0% to 6.7%, and the monitor nearly triples task success after environment restoration. Even then, a fired escalation is not yet a useful handoff: tickets reliably name the blocker but often omit the agent's own progress and verification status. Taken together, we argue that knowing when to stop therefore needs explicit support, both in the tool that lets an agent hand off and in the report it leaves behind.

cs.SE↗

arXiv2026

Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests

Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewrite tools and control flow. In practice, a user hands the same endpoint heterogeneous requests whose effective solutions require different tools, reasoning modes, and control flow. Optimizing one shared program leaves this division of work implicit in source-code search, while optimizing a separate program per request family fixes it beforehand. We introduce Adaptive-GEPA, which learns both how to divide requests and how to solve them. It evolves a router and a library of specialist programs under one search budget. The router's instructions, each specialist's description, and its program code are plain, human-readable text, edited from feedback. To combine branches, it aligns specialists by the requests they handle and inherits descriptions together with programs. On a fixed mixture of four task families, the reported Qwen3-8B run evolves four experts without supplying family labels to the router or reflection model; its routing matches the task partition on all 651 test requests. Its family-mean test score (x100) rises from 52.6 to 70.6, compared with 62.5 for GEPA's full-program adapter and 54.0 for GRPO at a nominal budget of 18,000 scored calls. These counts do not equate total compute. Figure 1 summarizes the learning curves, final test scores, and routing agreement.

cs.SE↗

arXiv2026

Efficient Test-Time Adaptation through Human-AI Interaction

AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are heterogeneous and insufficiently documented, individual expertise lives precisely in the elevation and departure from the average. In practice, iterative human-agent interaction surfaces criteria that users cannot fully specify up front, yet apply repeatedly across tasks. We argue this cross-session interaction data is a rich, underused signal for closing the gap to individual expertise. In this work, we propose test-time adaptation through human-agent interaction (TAHI), which integrates these signals into agent context and weights, and crystallizes each user's training and evaluation criteria via an evolving rubric module. We adapt agents to 30 individuals in two high-utility domains, writing and visual creation, on a total of 600 tasks. Our agents improve solo task success by 4.5-20.9% within only tens of tasks. Meanwhile, our evolving rubric module serves as a scalable annotation tool, creating evaluation rubrics that catch 16.0-22.3% more failures than those from LMs or humans alone. While agents are adapted towards individuals, we show these personalized agents also produce improvements in success of up to 8.8% that generalize across users.

cs.AI↗

arXiv2026

Improving Attributed Long-form Question Answering with Intent Awareness

Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes and intents that guide authors in crafting these documents. We hypothesize that enhancing a model's intent awareness can significantly improve the quality of generated long-form reports. We develop and employ structured, tag-based schemes to better elicit underlying implicit intents to write or cite. We demonstrate that these extracted intents enhance both zero-shot generation capabilities in LLMs and enable the creation of high-quality synthetic data for fine-tuning smaller models. Our experiments reveal improved performance across various challenging scientific report generation tasks, with an average improvement of +2.9 and +12.3 absolute points for large and small models over baselines, respectively. Furthermore, our analysis illuminates how intent awareness enhances model citation usage and substantially improves report readability.

cs.CL↗

arXiv2026

AgentSociety 2: An Integrated Research Environment for Executable Social Science

AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or laboratory protocols, but integrated social processes involving situated participants, interaction contexts, interventions, and outcomes. Yet a critical link is missing: existing systems either assist isolated research tasks or simulate agents as experimental subjects, leaving the research workflow and simulated society decoupled. Here we introduce AgentSociety 2, an Integrated Research Environment for executable social science. It couples two roles of LLM agents in the same runtime: AI social scientists that coordinate literature grounding, hypothesis generation, experiment design, simulation execution, result interpretation, and manuscript drafting; and silicon participants that generate behavioral responses within configurable social environments. This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow. Across seven illustrative studies spanning micro-level social-science laboratory experiments, meso-level dynamics in social media, and macro-level urban scenarios, we demonstrate its capacity to support diverse disciplinary questions, reproduce major qualitative patterns from prior studies, identify informative deviations, and enable large-scale simulations through optimized agent-environment interactions. By preserving human researchers' high-level agency while delegating procedural orchestration to agentic systems, it provides a human-in-the-loop and controllable infrastructure for next-generation computational social science, with broader applications in scalable computational social experimentation and AI-enabled social governance platforms.

cs.CY↗

arXiv2026

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation

Frontier LLM agents are automating many business tasks, but their high inference cost makes large-scale deployment unsustainable. Small language models (SLMs) offer a cheaper alternative, yet they typically fall short when swapped into a harness designed for a frontier LLM. We show that for many routine business tasks, SLM agents can match LLM performance at 90% lower cost, when paired with an adapted harness that can be automatically discovered by a meta agent. The key insight is that much of the task difficulty is shared across instances and can be lifted from the model into the harness via tailored instructions, tools, and orchestration loops. To study this systematically, we create a framework that maps agent failure modes to harness adaptation strategies, and build a harness optimizer that automatically discovers effective adaptations from failure trajectories. Across seven business-oriented agentic tasks and three SLM families, we found optimized harnesses significantly improve performance on 16 of 21 task-SLM pairs, with seven pairs closing the SLM-LLM performance gap and the best SLM agent recovering 89.7% of LLM performance at 4% of the cost. Our analysis further shows that adaptation works best for tasks with more repetitive workflows and for SLMs with sufficient base capabilities. Together, these results suggest that harness adaptation can expand the practical deployment range of SLM agents in routine business tasks.

cs.SE↗

arXiv2026

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with Reinforcement Learning with Evolving Rubrics (RLER), where rubrics are constructed and maintained to co-evolve with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop Deep Research Tulu (DR Tulu-8B), the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).

cs.CL↗

arXiv2026

Revela: Dense Retriever Learning via Language Modeling

Dense retrievers play a vital role in accessing external and specialized knowledge to augment language models (LMs). Training dense retrievers typically requires annotated query-document pairs, which are costly to create and scarce in specialized domains (e.g., code) or in complex settings (e.g., requiring reasoning). These practical challenges have sparked growing interest in self-supervised retriever learning. Since LMs are trained to capture token-level dependencies through a self-supervised learning objective (i.e., next token prediction), we can analogously cast retrieval as learning dependencies among chunks of tokens. This analogy naturally leads to the question: How can we adapt self-supervised learning objectives in the spirit of language modeling to train retrievers? To answer this question, we introduce Revela, a unified and scalable training framework for self-supervised retriever learning via language modeling. Revela models semantic dependencies among documents by conditioning next token prediction on local and cross-document context through an in-batch attention mechanism. This attention is weighted by retriever-computed similarity scores, enabling the retriever to be optimized as part of language modeling. We evaluate Revela on domain-specific (CoIR), reasoning-intensive (BRIGHT), and general-domain (BEIR) benchmarks across various retriever backbones. Without annotated or synthetic query-document pairs, Revela surpasses larger supervised models and proprietary APIs on both CoIR and BRIGHT. It achieves BEIR's unsupervised SoTA with ~1000x less training data and 10x less compute. Performance increases with batch size and model size, highlighting Revela's scalability and its promise for self-supervised retriever learning.

cs.IR↗

arXiv2025

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters

Winning competitive debates requires sophisticated reasoning and argument skills. There are unique challenges in the competitive debate: (1) The time constraints force debaters to make strategic choices about which points to pursue rather than covering all possible arguments; (2) The persuasiveness of the debate relies on the back-and-forth interaction between arguments, which a single final game status cannot evaluate. To address these challenges, we propose TreeDebater, a novel debate framework that excels in competitive debate. We introduce two tree structures: the Rehearsal Tree and Debate Flow Tree. The Rehearsal Tree anticipates the attack and defenses to evaluate the strength of the claim, while the Debate Flow Tree tracks the debate status to identify the active actions. TreeDebater allocates its time budget among candidate actions and uses the speech time controller and feedback from the simulated audience to revise its statement. The human evaluation on both the stage-level and the debate-level comparison shows that our TreeDebater outperforms the state-of-the-art multi-agent debate system, with a +15.6% improvement in stage-level persuasiveness with DeepSeek and +10% debate-level opinion shift win. Further investigation shows that TreeDebater shows better strategies in limiting time to important debate actions, aligning with the strategies of human debate experts.

cs.CL↗

arXiv2025

RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, conflicting between internal and external retrieved contexts, or fast-changing facts. We introduce Retrieval-Aware Robustness Evaluation (RARE), a unified framework and large-scale benchmark that jointly stress-tests query and document perturbations over dynamic, time-sensitive corpora. One of the central features of RARE is a knowledge-graph-driven synthesis pipeline (RARE-Get) that automatically extracts single and multi-hop relations from the customized corpus and generates multi-level question sets without manual intervention. Leveraging this pipeline, we construct a dataset (RARE-Set) spanning 527 expert-level time-sensitive finance, economics, and policy documents and 48295 questions whose distribution evolves as the underlying sources change. To quantify resilience, we formalize retrieval-conditioned robustness metrics (RARE-Met) that capture a model's ability to remain correct or recover when queries, documents, or real-world retrieval results are systematically altered. Our findings reveal that RAG systems are unexpectedly sensitive to perturbations. Moreover, they consistently demonstrate lower robustness on multi-hop queries compared to single-hop queries across all domains.

cs.CL↗

arXiv2025

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree

Retrieval-Augmented Generation (RAG) has become essential for large-scale code generation, grounding predictions in external code corpora to improve actuality. However, a critical yet underexplored aspect of RAG pipelines is chunking -- the process of dividing documents into retrievable units. Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code, which can degrade generation quality. We propose chunking via Abstract Syntax Trees (\ourwork), a structure-aware method that recursively breaks large AST nodes into smaller chunks and merges sibling nodes while respecting size limits. This approach generates self-contained, semantically coherent units across programming languages and tasks, improving performance on diverse code generation tasks, e.g., boosting Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation. Our work highlights the importance of structure-aware chunking for scaling retrieval-enhanced code intelligence.

cs.SE↗

arXiv2025

The Ramon Llull's Thinking Machine for Automated Ideation

This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern Llull's thinking machine for research ideation. Our approach defines three compositional axes: Theme (e.g., efficiency, adaptivity), Domain (e.g., question answering, machine translation), and Method (e.g., adversarial training, linear attention). These elements represent high-level abstractions common in scientific work - motivations, problem settings, and technical approaches - and serve as building blocks for LLM-driven exploration. We mine elements from human experts or conference papers and show that prompting LLMs with curated combinations produces research ideas that are diverse, relevant, and grounded in current literature. This modern thinking machine offers a lightweight, interpretable tool for augmenting scientific creativity and suggests a path toward collaborative ideation between humans and AI.

cs.AI↗

arXiv2025

MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers

Retrieval-augmented Generation (RAG) is powerful, but its effectiveness hinges on which retrievers we use and how. Different retrievers offer distinct, often complementary signals: BM25 captures lexical matches; dense retrievers, semantic similarity. Yet in practice, we typically fix a single retriever based on heuristics, which fails to generalize across diverse information needs. Can we dynamically select and integrate multiple retrievers for each individual query, without the need for manual selection? In our work, we validate this intuition with quantitative analysis and introduce mixture of retrievers: a zero-shot, weighted combination of heterogeneous retrievers. Extensive experiments show that such mixtures are effective and efficient: Despite totaling just 0.8B parameters, this mixture outperforms every individual retriever and even larger 7B models by +10.8% and +3.9% on average, respectively. Further analysis also shows that this mixture framework can help incorporate specialized non-oracle human information sources as retrievers to achieve good collaboration, with a 58.9% relative performance improvement over simulated humans alone.

cs.IR↗

arXiv2025

Improving Large Language Model Planning with Action Sequence Similarity

Planning is essential for artificial intelligence systems to look ahead and proactively determine a course of actions to reach objectives in the virtual and real world. Recent work on large language models (LLMs) sheds light on their planning capability in various tasks. However, it remains unclear what signals in the context influence the model performance. In this work, we explore how to improve the model planning capability through in-context learning (ICL), specifically, what signals can help select the exemplars. Through extensive experiments, we observe that commonly used problem similarity may result in false positives with drastically different plans, which can mislead the model. In response, we propose to sample and filter exemplars leveraging plan side action sequence similarity (AS). We propose GRASE-DC: a two-stage pipeline that first re-samples high AS exemplars and then curates the selected exemplars with dynamic clustering on AS to achieve a balance of relevance and diversity. Our experimental result confirms that GRASE-DC achieves significant performance improvement on various planning tasks (up to ~11-40 point absolute accuracy improvement with 27.3% fewer exemplars needed on average). With GRASE-DC* + VAL, where we iteratively apply GRASE-DC with a validator, we are able to even boost the performance by 18.9% more. Extensive analysis validates the consistent performance improvement of GRASE-DC with various backbone LLMs and on both classical planning and natural language planning benchmarks. GRASE-DC can further boost the planning accuracy by ~24 absolute points on harder problems using simpler problems as exemplars over a random baseline. This demonstrates its ability to generalize to out-of-distribution problems.

cs.AI↗

arXiv2025

Throughput-Optimal Random Access: A Queueing-Theoretical Analysis for Learning-Based Access Design

Random access networks have long been observed to suffer from low throughput if nodes' access strategy is not properly designed. To improve the throughput performance, learning-based approaches, with which each node learns from the observations and experience to determine its own access strategy, have shown immense potential, but are often designed empirically due to the lack of theoretical guidance. As we will demonstrate in this paper, the queueing-theoretical analysis can be leveraged as a powerful tool for optimal design of learning-based access. Specifically, based on a Multi-Armed-Bandit (MAB) framework, two random access schemes, MTOA-L with local rewards and MTOA-G with global rewards, are proposed for throughput optimization. Though both can achieve the maximum throughput of 1, they have different short-term fairness performance. Through identifying the access strategies learned via MTOA-L and MTOA-G and feeding them into the proposed unified queueing-theoretical framework, the throughput-fairness tradeoff of each is characterized and optimized by properly tuning the key parameters. The comparison of the optimal tradeoffs shows that MTOA-G is much superior to MTOA-L especially when the number of nodes is large.

cs.NI↗

arXiv2025

SPHERE: An Evaluation Card for Human-AI Systems

In the era of Large Language Models (LLMs), establishing effective evaluation methods and standards for diverse human-AI interaction systems is increasingly challenging. To encourage more transparent documentation and facilitate discussion on human-AI system evaluation design options, we present an evaluation card SPHERE, which encompasses five key dimensions: 1) What is being evaluated?; 2) How is the evaluation conducted?; 3) Who is participating in the evaluation?; 4) When is evaluation conducted?; 5) How is evaluation validated? We conduct a review of 39 human-AI systems using SPHERE, outlining current evaluation practices and areas for improvement. We provide three recommendations for improving the validity and rigor of evaluation practices.

cs.HC↗

arXiv2025

Thrust: Adaptively Propels Large Language Models with External Knowledge

Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However, the existing information retrieval techniques could be costly and may even introduce noisy and sometimes misleading knowledge. To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary. To achieve this goal, we propose measuring whether a PTLM contains enough knowledge to solve an instance with a novel metric, Thrust, which leverages the representation distribution of a small number of seen instances. Extensive experiments demonstrate that thrust is a good measurement of PTLM models' instance-level knowledgeability. Moreover, we can achieve significantly higher cost-efficiency with the Thrust score as the retrieval indicator than the naive usage of external knowledge on 88% of the evaluated tasks with 26% average performance improvement. Such findings shed light on the real-world practice of knowledge-enhanced LMs with a limited knowledge-seeking budget due to computation latency or costs.

cs.CL↗