Searcharxiv⌕ Search

arXiv subjects

Guanhua Chen

Publications and source records attributed to Guanhua Chen.

At least 19 recordsLinked to original sources
arXiv2026

LAMP: LLM-Driven Analog Placement through Adaptive Tool Composition

Analog placement requires circuit-specific trade-offs among area, matching, routability, and electrical performance. Balancing these trade-offs through predefined objectives and fixed placement flows remains difficult. In this paper, we propose an analog placement framework in which a large language model (LLM) acts as a layout engineer through composable placement components. These components support constraint management, placement and legalization, and lightweight evaluation of routability and electrical performance. Using multimodal checkpoints of the initial and evolving design, the LLM selects and combines components to construct and revise its own placement flow. It also adapts the placement hierarchy by reopening modules or partitioning and regrouping devices, allowing local layouts to respond to global design needs. An experience skill provides reusable design knowledge to guide these decisions. Evaluation on two SMIC 180 nm circuits shows that the framework reduces placement area and improves most measured post-layout performance metrics.

cs.AR↗
arXiv2026

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and turn intermediate results into final deliverables. High-quality long-horizon trajectories capture these agentic behavioral patterns and their connections within a single problem-solving process, providing richer experience for sustained autonomous work. However, environment synthesis may complete or simplify the key work underlying these patterns in advance and thus remove the need for exploration, implementation, and verification that the agent was meant to perform. To address this, we introduce TerminalHorizon, a fully automated data synthesis engine for long-horizon terminal agents. Starting from real-world professional work, it uses independent execution to identify key work omitted during construction and uses the resulting evidence to guide environment reconstruction. To extend these patterns across stages, it progressively expands tasks under the same goal, introducing new requirements that build on prior results and call for further exploration and improvement. Using this engine, we construct 1.5K task environments and perform supervised fine-tuning of Qwen3.5-27B on the resulting dataset to obtain TerminalHorizon-27B. We achieve substantial performance gains on all 12 benchmarks spanning coding-agent tasks, agentic tasks in real-world production settings, and general reasoning. Multiple RSI case studies, each with a 12-hour research budget, further demonstrate the model's ability to continue experimenting beyond an initial solution, improve its methods based on feedback, and retain effective improvements in its final deliverables.

cs.CL↗
arXiv2026

StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions

We introduce StartLux-Decision, decision models from 0.8B to 27B parameters that combine efficient single-pass prediction with adaptive, confidence-guided reasoning. The Instant models use bidirectional attention in full-attention layers to improve decision accuracy while keeping single-pass inference. The AutoThink models invoke explicit reasoning for uncertain decisions and answer confident cases directly. A three-stage training pipeline establishes shared decision capabilities, specializes the two variants, and equips AutoThink with reasoning through reasoning supervision and reinforcement learning. We introduce Reinforcement Learning for Calibrated Deliberative Decisions (RLCD$^2$), which uses a frozen model and proper scoring rules to reward improvements in decision probability quality and applies a soft penalty to overlong reasoning traces. RLCD$^2$ raises the share of reasoning traces that terminate within the generation limit by up to 48 percentage points and cuts average reasoning length by up to 65%, while largely preserving decision accuracy. On the public subset of Decision Index 0.3, the Instant models outperform the strongest evaluated comparable-scale open-weight decision models by 7.4-16.9 points, and the 27B AutoThink model reaches 73.4. We also introduce DecisionPivot, a programmatically verifiable benchmark of computational decisions built from contrast pairs that differ in a single answer-changing detail. On DecisionPivot, AutoThink outperforms its Instant counterparts by 11.5-18.4 points in pair accuracy and leads among evaluated systems. The models can be run using frameworks such as vLLM and MLX, with quantized versions available to reduce memory usage.Inference code and links to model weights are available at https://github.com/StartLuxLabs/Startlux-Decision .

cs.CL↗
arXiv2026

DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems

Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions across controlled variations or assign reliable confidence to their predictions. We introduce DecisionPivot, a diagnostic benchmark comprising 48 tasks and 40,033 items across seven decision roles. Its core track contains 7,800 items from 13 generated task families, organized into contrast groups with computed answers verified by independently implemented solvers. The complementary reference track contains 32,233 items from 35 public test sets, preserving their original evaluation metrics. We evaluate 40 decision models and 14 general models using documented, model-specific protocols, assessing item and contrast-group accuracy, probability ordering, calibration, and empirical selective coverage. Our results reveal substantial differences obscured by aggregate scores: two 27B models separated by only 2.6 points on the reference track achieve contrast-group accuracies of 70.1% and 44.2%. Across 2,400 binary contrast pairs, Perplexity Decider correctly ranks the positive member above the negative member in 92.3% of pairs but answers both members correctly in only 74.1%, exposing a gap between probability ordering and decision correctness. Models with similar item accuracy also differ in the reliability of their high-confidence predictions. On a separate 1,296-item subset, GLM-5.3 achieves 93.5\% contrast-group accuracy at a higher reasoning setting, compared with 81.5% at its lowest effort. By linking errors to pivotal details and difficulty levels, DecisionPivot provides fine-grained diagnostics of decision failures that aggregate evaluation alone cannot reveal.

cs.AI↗
arXiv2026

How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices

Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks, benchmarks, and studies that are difficult to compare directly. We review this literature from the perspective of evaluation design and evidence, covering six targets: literature synthesis, research ideation, executable workflows, scholarly writing and communication, automatic peer review, and end-to-end research. We compare task construction, evidence sources, evaluators, and scoring procedures to explain the capabilities assessed by different designs. Our synthesis highlights three recurring lessons: output checks, process checks, and human studies provide complementary information; evaluator calibration is specific to the property being assessed; and resource budgets and attempt selection are integral to interpreting performance comparisons. We identify diagnostic evaluation designs and documented gaps in supporting evidence, and translate these comparisons into reporting and audit recommendations for specific evaluation settings. The survey helps readers navigate existing evaluations, select appropriate benchmarks, and design subsequent studies.

cs.AI↗
arXiv2026

Sliced $L^p$ Distributional Balancing

A popular class of causal inference methods addresses confounding through weighting, which reweights treated and control groups to balance their covariate distributions without using outcome information, thereby preserving a design-based perspective. In this paper, we propose sliced $L^p$ distributional balancing (SLDB), a family indexed by $p\in[1,\infty)$ that measures imbalance by averaging squared $L^p$ distances between the cumulative distribution functions of one-dimensional linear projections. The Cramér--Wold device ensures that this criterion identifies equality of multivariate distributions, while projection reduces its computation to sorting-based one-dimensional operations. Because our method lies outside the maximum mean discrepancy (MMD) framework underlying many existing distributional balancing methods, their theoretical and computational tools do not directly apply. We therefore develop a computationally efficient projected subgradient descent algorithm for estimating balancing weights, offering improved computational complexity over MMD-based methods. Furthermore, we establish a novel theoretical framework for SLDB-based causal effect estimation and prove, under suitable conditions, root-n consistency and asymptotic normality, with the asymptotic variance attaining the semiparametric efficiency bound. Finally, we develop inferential procedures that do not require augmentation with an outcome model, thereby retaining the design-based principle. Simulation studies and a real-world application demonstrate that SLDB performs competitively with existing methods.

stat.ME↗
arXiv2026

Weighted Spline-Expanded Networks with Distributional Balancing for Continuous Treatment Effects

Estimating causal effects with continuous treatments in observational studies is challenging due to confounding, model misspecification, and high-dimensional covariates. We propose the Weighted Spline-Expanded Network (WSENet), an end-to-end neural framework that addresses these challenges by combining covariate balancing, structured treatment embedding, and bias-corrected outcome estimation. WSENet first applies Distance Covariate Optimal Weights to induce distributional independence between covariates and treatment without relying on parametric models. It then learns the conditional outcome via a structured network that fuses outcome-relevant representations of covariates with a spline-expanded treatment input, enabling smooth and flexible modeling of the dose-response relationship. To mitigate residual bias, we introduce Weighted Targeted Regularization, a correction technique based on efficient influence functions that yields a doubly robust estimator. Extensive evaluations on semi-synthetic and real-world datasets, including high-dimensional genomic and environmental health data, demonstrate that WSENet consistently outperforms existing baselines in both accuracy and stability.

stat.ML↗
arXiv2026

Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions

Large language models (LLMs) demonstrate remarkable performance across various tasks, prompting researchers to develop diverse evaluation benchmarks. However, most benchmarks typically measure the ability of LLMs to respond to individual questions, neglecting the complex interactions in real-world applications. We introduce Compound Question Synthesis (CQ-Syn) to build Compound-QA, a benchmark targeting questions composed of multiple interrelated sub-questions. This benchmark is derived from existing QA datasets, annotated with proprietary LLMs, and verified by humans for accuracy. It encompasses five categories: Factual-Statement, Cause-and-Effect, Hypothetical-Analysis, Comparison-and-Selection, and Evaluation-and-Suggestion. It evaluates the LLM capability in terms of three dimensions, including understanding, reasoning, and knowledge. Evaluating nine open-source LLMs on Compound-QA reveals that their performance on compound questions is notably lower than on non-compound questions. We further explore strategies to enhance LLMs' handling of compound questions, and our results show that these methods substantially improve models' comprehension and reasoning abilities.

cs.CL↗
arXiv2026

JustMem: Just-Enough Memory Access for Long-Term Conversations

Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the language model. This is challenging because relevant evidence may be distributed across multiple sessions, while compression may discard details needed for answering. Different queries therefore require different forms of memory access. To capture these demands, we formulate memory access along two dimensions: discovery breadth, which controls how broadly evidence is searched, and reading fidelity, which controls whether evidence is read in compact form or recovered from the original conversation. Based on this formulation, we introduce JustMem, which stores conversation history as compact atomic memories and adapts memory access along these two dimensions to each query. Specifically, LOOKUP handles local evidence, COMPOSE broadens discovery for distributed evidence, and REPLAY increases reading fidelity for fidelity-sensitive evidence. On LoCoMo and LongMemEval-S, JustMem achieves the highest mean accuracy and retrieval recall among the compared memory systems while using substantially fewer generative-model tokens for memory construction and inference.

cs.CL↗
arXiv2026

Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence

Large Language Models (LLMs) are increasingly applied to legal and criminal justice tasks, yet existing work focuses almost exclusively on post-arrest scenarios where the suspect's identity is already known, leaving the critical pre-arrest challenge of inferring suspect characteristics from incomplete evidence largely unexplored. To fill this gap, we introduce the Profiling, Investigation, and Judgment (PIJ), comprising 2,500 real homicide cases from five countries. PIJ evaluates LLMs across three tasks that span the entire criminal investigation pipeline: criminal profiling, which requires abductive reasoning to infer suspect attributes from fragmentary scene evidence, crime process reconstruction, which tests structured information extraction, and sentence prediction, which demands legal deductive reasoning. We evaluate 9 powerful LLMs and find that performance degrades systematically as tasks shift from explicit fact extraction to implicit reasoning over unknown suspect profiles. Categories requiring inferential reasoning, such as motivation and victim-offender relationships, remain the primary bottlenecks. Further analysis reveals substantial gaps between LLMs and human experts, along with pervasive biases in gender, age, and motive attribution. Our findings indicate that pre-arrest inference from incomplete evidence remains an open challenge.

cs.CL↗
arXiv2026

Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training

Clinical education must prepare medical students to conduct safe and coherent patient interviews under conditions of uncertainty. Traditional standardized patient (SP) training is resource-intensive and difficult to scale. We developed a scaffolding-oriented multi-agent Large Language Model (LLM) AI Standardized Patient (AI-SP) training platform1. The system includes a patient agent for simulated dialog, a tutor agent providing Socratic prompts without disclosing diagnostic information, and a turn-level evaluator agent that monitors clinical progress without revealing summative scores. In a randomized controlled study (N = 100 medical students), participants were assigned to either a multi-agent (MA) scaffolding condition or a control condition. All students completed two learning sessions under their assigned condition followed by an examination conducted in a patient only environment. Performance was assessed using a standardized Objective Structured Clinical Examination (OSCE) based rubric. While no significant difference was observed in final diagnostic accuracy between groups, the multi-agent AI standardized patient system improved final examination scores compared to the control group utilizing structured progressive information disclosure; the most substantial and consistent improvements were observed in communication, the expression of empathy, and specific history-taking behaviors. These findings suggest that specialized LLM agents enhance the process quality of simulated clinical interviews without artificially inflating examination outcomes. To support future research, we release a multi-expert annotated dataset comprising transcripts, checklist annotations, turn-level evaluations, and OSCE-aligned scoring outcomes. This resource aims to facilitate the development of pedagogically grounded AI-SP systems and advance research on AI-supported clinical reasoning training.

cs.MA↗
arXiv2026

ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations

Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieval and direct comparison between observations. Yet accumulating atoms inevitably become redundant, overlapping, or conflicting. Existing methods often ask an LLM manager to add, update, delete, or rewrite memories directly, coupling semantic interpretation, storage decisions, and content generation in one error-prone operation. We introduce ROAM, a relation-guided framework that uses atomicity for management while allowing richer answer-time representations. ROAM classifies incoming--stored atom pairs as independent, equivalent, directionally subsuming, or conflicting, then organizes observations into active Primary and supporting Evidence roles. Fusion subsequently combines complementary details and temporal changes into compact, potentially non-atomic views. Only Primary views are retrieved for answering, preventing redundant or outdated atoms from competing independently. Across models and evaluation settings, ROAM improves answer accuracy by up to 29.8 percentage points. Ablations show complementary benefits from different relations and consistent gains from fusion beyond role organization. Mechanism analysis further finds 15.6-point higher answer-critical source recall and an 11.5-point lower confounder-token share. ROAM remains robust across manager scales.

cs.CL↗
arXiv2026

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2). While System 2 reasoning improves task accuracy, it often incurs substantial computational costs due to its slow thinking nature and inefficient or unnecessary reasoning behaviors. In contrast, System 1 reasoning is computationally efficient but leads to suboptimal performance. Consequently, it is critical to balance the trade-off between performance (benefits) and computational costs (budgets), giving rise to the concept of reasoning economy. In this survey, we provide a comprehensive analysis of reasoning economy in both the post-training and test-time inference stages of LLMs, encompassing i) the cause of reasoning inefficiency, ii) behavior analysis of different reasoning patterns, and iii) potential solutions to achieve reasoning economy. By offering actionable insights and highlighting open challenges, we aim to shed light on strategies for improving the reasoning economy of LLMs, thereby serving as a valuable resource for advancing research in this evolving area. We also provide a public repository to continually track developments in this fast-evolving field.

cs.CL↗
arXiv2026

NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management

An embodied kitchen assistant must do more than recognize food in isolated frames. It must track ingredient states over time and integrate visual observations with recipe and nutritional knowledge to support constraint-aware decision-making. We formalize this capability as \emph{Embodied Nutrition Management}: perceiving nutrition-relevant events, maintaining a persistent food state, and using it for knowledge-grounded planning. Existing benchmarks evaluate static food understanding or embodied cooking actions, but do not measure whether an agent can continuously update and use nutrition-relevant states in dynamic kitchens. To fill this gap, we introduce \textbf{NutriBench-Kitchen}, a benchmark containing 1,500 manually verified question--answer pairs from 160 cooking videos. It covers five task families: Ingredient Entry, Memory Management, Recipe Query, Long-Term Planning, and Short-Term Planning, spanning food-state construction, maintenance, knowledge retrieval, and decision-making across different planning horizons. Evaluations of proprietary and open-source large vision-language models reveal a substantial gap from human performance, particularly in quantitative ingredient estimation, long-term state tracking, and reasoning under interacting constraints. We further introduce \textbf{Nutri-Vgent}, a diagnostic long-video agent with separate episodic, food-state, and recipe memories. Its consistent improvements demonstrate the value of explicit state representations and structured memory for nutrition management. Together, NutriBench-Kitchen and Nutri-Vgent provide a testbed for studying persistent state tracking and knowledge-grounded reasoning in dynamic kitchens. Code is available at https://github.com/V1ol1n/NutriBench-Kitchen.

cs.CV↗
arXiv2026

AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection

Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective alignment. Existing datasets are frequently plagued by inherent noise and distribution shifts, which inherently limit model performance. To bridge this gap, we propose AlignDiff, a preference data filtering framework driven by intrinsic model signals. AlignDiff first identifies samples with clear preferences using both positive and inverse signals, then prioritizes the more challenging samples based on the average negative log-likelihood gap, encouraging the model to learn richer information from them. AlignDiff is evaluated on two widely used model families (LLaMA and Qwen) and three benchmarks widely adopted in the alignment community (AlpacaEval 2.0, Arena-Hard, and MT-Bench). Across all settings, it consistently outperforms seven strong baselines. We conduct comprehensive ablation studies to validate the effectiveness of AlignDiff, and further show that difficulty-based curriculum learning improves model performance.

cs.CL↗
arXiv2026

UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms

Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challenge. Existing solutions either depend on costly proprietary LLM-as-a-Judge systems or opaque scalar reward models that lack interpretability. Recent works on generative reward models offer a promising alternative, but they remain constrained by static evaluation criteria, fragmented evaluation paradigms, and limited multilingual support. To address these challenges, we introduce \textbf{MixReward}, a large-scale multilingual dataset spanning six domains and 103 languages, containing both pairwise and listwise data, and propose \textbf{UniRRM}, a unified reasoning reward model supporting multiple languages and evaluation paradigms. UniRRM uses a staged reasoning chain to dynamically generate task-generic and instruction-specific criteria, enabling fine-grained, input-adaptive judgments while maintaining consistency across languages. Experiments demonstrate that UniRRM-8B and UniRRM-14B achieve performance close to the state-of-the-art for models of comparable size across multiple benchmarks, and are effective for unseen evaluation paradigms. In addition, ablation studies validate the reliability and effectiveness of UniRRM.

cs.CL↗
arXiv2026

Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction

Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g., templates, separators, boilerplate) that do not reflect patient state. We propose CAST (Concept-guided Artifact Suppression Tuning), an SAE-based framework for auditable clinical text classification. CAST uses Sparse Autoencoders to expose sparse, human-auditable features from intermediate Transformer activations, labels SAE latents with an LLM-assisted interpretation pipeline and ICD-10 retrieval constraints, suppresses verified artifact latents via residual subtraction during fine-tuning, and provides post-hoc per-concept attributions for auditing model decisions. On MIMIC-IV discharge-note mortality prediction, CAST improves over its corresponding fine-tuned encoder baselines and remains competitive with strong LLM baselines, while producing a feature-level audit trail of the clinical concepts that support each prediction and the artifact concepts suppressed during training.

cs.CL↗
arXiv2026

Causal Generalization of Continuous Treatment Effects under Covariate Shift

Average dose-response functions are widely used to summarize causal effects of continuous treatments, but most existing methods assume that the observed sample represents the target population. We study a covariate-shift setting in which covariates, treatment, and outcome are observed in a labelled source sample, while only covariates are observed in the target sample. We develop a two-sample local polynomial regression framework based on pseudo-outcomes that use source outcomes to address confounding and target covariates to define the population of interest. We further propose a source-to-target extension of distance covariance optimal weighting (DCOW), designed to remove treatment-covariate dependence in the source sample while aligning the weighted source covariate distribution with the target population. A central theoretical contribution is a weight-level analysis of this optimization-based procedure: we show that the population criterion identifies the oracle source-to-target weights and that approximate empirical minimizers, including exact minimizers as a special case, converge uniformly to these weights under regularity conditions. We also establish consistency and asymptotic normality of the resulting estimator. Simulations show that the proposed method improves target dose-response estimation relative to DCOW, generalized-propensity-score weighting, entropy balancing, and unweighted alternatives. We illustrate the method in a county-level analysis of PM2.5 exposure and subsequent heart-disease mortality using a source-target validation design.

stat.ME↗