Xujiang Zhao was a researcher in the Data Science & System Security department at NEC Laboratories America, based in Princeton, New Jersey.

Posts

Escaping Whack-a-Mole: Optimizing Documentation as Repo-Specific Playbooks for Coding Agents

/in /by

As large language models increasingly serve as autonomous coding agents, code documentation must be optimized for agent comprehension rather than human readability. We frame agent-oriented documentation generation as a black-box optimization problem over the documentation space, where quality is measured solely by downstream code correctness. A central challenge for conventional LLM refinement methods is output coupling—program entities are interdependent, and refining the documentation of one entity can invalidate its callers, resulting in a persistent whack-a-mole phenomenon during inference-time scaling. We propose DocSearch, a dependency-guided bi-level search framework that systematically exploits test-time feedback. The outer level conducts a priority search over the program-entity dependency DAG, enforcing a callee-before-caller refinement order to prevent downstream interference. The inner level performs a beam search over documentation refinements, using diversified error message sampling from self-generated unit tests to better exploit diagnostic signals and escape local optima. We provide theoretical guarantees of monotonic progress, showing that our worthy condition prevents regression while enabling efficient exploration. On DevEval+, DocSearch achieves a 90.7% solve rate with GPT-4o, outperforming the strongest baseline by 32.6%. Cross-language experiments further demonstrate that optimized documentation transfers effectively to different target programming languages.

Read more

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs

/in /by

Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and accurate knowledge up-dates without costly retraining are a major challenge. This problem is particularly challenging in lifelong settings, where complex, unstructured knowledge must coexist without interference. We introduce RILKE (Representation Intervention for Lifelong KnowledgE Control), a robust and scalable method that treats knowledge control as interventions within the model’s representation space. Leveraging representation-space expressiveness, we identify two key properties enabling RILKE to achieve fine-grained control over complex, un-structured knowledge while maintaining general utility with frozen base weights. During training, RILKE learns paraphrase-robust and edit-localized modules that limit each update to a low-dimensional subspace to minimize cross-edit interference. At inference, a query-adaptive router selects the appropriate module to guide the model’s generation. Across LLaMA and Qwen models, RILKE scales effectively to large-scale benchmarks, demonstrating high edit success and strong paraphrase generalization while preserving general utility with modest memory overhead. These results show RILKE is an effective and scalable solution for lifelong knowledge control in LLMs.

Read more

Uncertainty-Aware Test-Time Search for Optimization Problem Solving

/in /by

Automatically solving optimization problems from natural language descriptions with both efficiency and reliability is highly desirable but remains challenging. Language model hallucinations and the limited availability of labeled datasets often result in misaligned formulations, code errors, and feasibility failures. We pro-pose UMCTS, an Uncertainty-aware Monte Carlo Tree Search framework that combines the language understanding capability of large language models with the reliability of well-established solvers. UMCTS structures the solution process into four stages: global instruction, assumptions, mathematical formulation, and solver code generation. It employs Monte Carlo Tree Search with semantic-equivalence pruning, prior-guided exploration, and solver-based feasibility checks. An LLM judge provides numerical reward signals, qualtative error information, and uncertainty estimates. These signals are backpropagated to guide the search and flag unreliable out-puts. Across six public benchmarks, UMCTS achieves state-of-the-art solution accuracy and improves efficiency by reducing token usage.

Read more

Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models

/in /by

Large language models (LLMs) are increasingly deployed in culturally sensitive real-world tasks. However, existing cultural alignment ap-roaches fail to align LLMs’ broad cultural values with the specific goals of downstream tasks and suffer from cross-culture interference. We propose CultureManager, a novel pipeline for task-specific cultural alignment. CultureManager synthesizes task-aware cultural data in line with target task formats, grounded in culturally relevant web search results. To prevent conflicts between cultural norms, it manages multi-culture knowledge learned in separate adapters with a culture router that selects the appropriate one to apply. Experiments across five national cultures and ten culture-sensitive tasks show consistent improvements over prompt-based and fine-tuning baselines. Our results demonstrate the necessity of task adaptation and modular culture management for effective cultural alignment.

Read more

NEC Labs America Attends ACL 2026 San Diego July 2-7, 2026

/in /by

NEC Laboratories America heads to ACL 2026 in San Diego, California, July 2–7, to present accepted papers spanning knowledge updating and memory control in large language models, task-aware cultural alignment, uncertainty-aware reasoning, and adaptive chain-of-thought optimization, representing some of the most active frontiers in NLP and AI research today.

Read more

Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement

/in /by

Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural graph extraction, they often produce ill-formed structures or misinterpret logical flows. We present text2flow, a multi-agent framework that formulates procedural graph extraction as a multi-round reasoning process with dedicated structural and logical refinement. The framework iterates through three stages: (1) a graph extraction phase with the graph builder agent, (2) a structural feedback phase in which a simulation agent diagnoses and explains structural defects, and (3) a logical feedback phase in which a semantic agent aligns semantics between flow logic and linguistic cues in the source text. Important feedback is prioritized and expressed in naturallanguage, which is injected into subsequent prompts, enabling interpretable and controllable refinement. This modular design allows agents to target distinct error types without supervision or parameter updates. Experiments demonstrate that text2flow achieves substantial improvements in both structural correctness and logical consistency over strong baselines.

Read more

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router

/in /by

Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific information. Retrieval-Augmented Generation (RAG) has emerged as a promising solution, enabling LLMs to ground their responses in external sources. However, existing RAG methods lack fine-grained control over both the query and source sides, resulting in noisy retrieval, shallow reasoning, and limited adaptability to heterogeneous knowledge sources. In this work, we introduce DeepSieve, a novel RAG method that incorporates information sieving via LLM-as-a-knowledge-router. DeepSieve breaks down complex queries into structured sub-queries and recursively routes each to the most appropriate knowledge source, filtering out irrelevant information through a multi-stage information sieving process. This modular and transparent approach ensures that DeepSieve remains adaptable across diverse information needs. Experiments on three multi-hop QA benchmarks involving heterogeneous sources show that DeepSieve achieves greater reasoning depth, retrieval precision, and interpretability compared to conventional RAG approaches. Our codes are available at https://github.com/MinghoKwok/DeepSieve.

Read more

Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation

/in /by

Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time series and facilitating downstream tasks. However, obtaining such annotations is challenging, particularly in mission-critical domains. In this paper, we propose TESSA, a multi-agent system designed to automatically generate both general and domain-specific annotations for time series data. TESSA introduces two agents: a general annotation agent and a domain-specific annotation agent. The general agent captures common patterns and knowledge across multiple source domains, leveraging both time-series-wise and text-wise features to generate general annotations. Meanwhile, the domain-specific agent utilizes limited annotations from the target domain to learn domain-specific terminology and generate targeted annotations. Extensive experiments on multiple synthetic and real-world datasets demonstrate that TESSA effectively generates high-quality annotations, outperforming existing methods.

Read more

MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery

/in /by

Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph (DAG), existing methods often lack efficiency, making them unsuitable for online applications. In this paper, we propose MARLIN, an efficient multi-agent RL-based approach for incremental DAG learning. MARLIN uses a DAG generation policy that maps a continuous real-valued space to the DAG space as an intra-batch strategy, then incorporates two RL agents — state-specific and state-invariant — to uncover causal relationships and integrates these agents into an incremental learning framework. Furthermore, the framework leverages a factored action space to enhance parallelization efficiency. Extensive experiments on synthetic and real datasets demonstrate that MARLIN out-performs state-of-the-art methods in terms of both efficiency and effectiveness.

Read more

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

/in /by

Large Language Models (LLMs) offer promising capabilities for tackling complex reasoning tasks, including optimization problems. However, existing methods either rely on prompt engineering, which leads to poor generalization across problem types, or require costly supervised training. We introduce SolverLLM, a training-free framework that leverages test-time scaling to solve diverse optimization problems. Rather than solving directly, SolverLLM generates mathematical formulations and translates them into solver-ready code, guided by a novel Monte Carlo Tree Search (MCTS) strategy. To enhance the search process, we modify classical MCTS with (1) dynamic expansion for adaptive formulation generation, (2) prompt backpropagation to guide exploration via outcome-driven feedback, and (3) uncertainty backpropagation to incorporate reward reliability into decision-making. Experiments on six standard benchmark datasets demonstrate that SolverLLM outperforms both prompt-based and learning-based baselines, achieving strong generalization without additional training.

Read more