arXiv subjects

Lang Cao

Publications and source records attributed to Lang Cao.

At least 19 recordsLinked to original sources

arXiv2026

Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning

Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones. However, we show that the same request can elicit substantially different safety decisions under different traits assigned in the system prompt, a failure mode we call trait-induced safety variation. To measure this failure, we introduce refusal-based metrics: Trait-Induced Deviation measures dataset-level deviation from the no-trait baseline, while Trait-Induced Flip Rate measures whether the same request receives different safety decisions across traits. We then provide a representation-level analysis of the mechanism behind trait-induced safety shifts and find that traits perturb the model's safety representations within a low-dimensional subspace. To achieve trait-invariant safety, where safety behavior remains stable across traits, we introduce Trait-Invariant Safety Tuning (TIST), a simple yet effective self-distillation framework that aligns an LLM's trait-conditioned behavior with its no-trait behavior. Guided by our analysis, we further propose Trait-Subspace Neutralization (TraSN), an instantiation of TIST, which enforces invariance only within the identified trait subspace. Experiments show that TraSN improves trait-invariant safety and strengthens harmful-request safety while preserving general capability. Our results highlight traits as an important factor in LLM safety and robust model behavior.

cs.AI↗

arXiv2026

GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning

Clinical practice guidelines (CPGs) encode diagnostic criteria, but LLM systems typically retrieve guideline text or absorb it through training rather than execute its rules. We introduce GuideSkill, an external reasoning layer that compiles disease-specific criteria into executable functions returning ordinal diagnostic-support scores. GuideSkill-Zero is initialized from guidelines, while GuideSkill-Evo uses case--diagnosis pairs to refine covered skills and add missing diagnoses. At inference, an LLM proposes a differential diagnosis, grounds the features required by each matched skill, and fuses its ranking with the executed skill scores. Across four benchmarks and four backbones, GuideSkill-Zero improves macro-average accuracy over guideline RAG by 13.45% on average. GuideSkill-Evo achieves the highest macro-average for every backbone, improves over direct inference by 18.49% relatively, and increases gold-label skill coverage from 56.5% to 99.5%. On Qwen3.5-9B, it also exceeds the strongest parameter-update baseline by 11.16% without updating the backbone. Expert evaluation further indicates that GuideSkill produces clinically sound and broadly acceptable skills, suggesting that its initialized and evolved rules are reliable and practically meaningful. These results support executable skills as a model-agnostic mechanism for combining guideline-derived procedures with case-derived diagnostic patterns.

cs.AI↗

arXiv2026

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However, most existing policies remain limited by behavior cloning or supervised fine-tuning (SFT) from fixed demonstrations, which provides limited opportunity to improve from the policy's own failures. In this paper, we present Z-1, a reinforcement learning (RL) post-training framework for flow-based VLA models. Built on top of $\pi_{0.5}$, Z-1 uses only publicly released RoboCasa demonstrations for SFT and then applies a task-wise Group Relative Policy Optimization (GRPO) strategy across $24$ standard RoboCasa tasks. To improve the efficiency and stability of online optimization, Z-1 combines shared-prefix rollout construction, tree-structured trajectory branching, completion-aware reward calibration, and selective joint training of VLM and Action Expert. Across all $24$ RoboCasa tasks, Z-1 achieves an average success rate of $80.6\%$, improving over its SFT initialization by $13.2\%$ points and outperforms the published sota models. These results show that systematic GRPO post-training can substantially improve flow-based VLA policies without additional private demonstrations.

cs.RO↗

arXiv2026

Quantum tidal locking in orbiting Bose-Einstein condensates

Angular momentum coupling manifests widely in diverse physical systems, underpinning the emergent properties and collective dynamics across different scales. The tidal locking, which originates from the synchronization of rotational and orbital motions, has far-reaching impacts in celestial mechanics, reflecting fundamental processes of angular momentum transfer, energy dissipation, and evolution toward dynamical equilibrium. However, its counterpart in mesoscopic quantum fluids has remained largely unexplored. Here we demonstrate the emergence of quantum tidal locking in Bose-Einstein condensates undergoing central force motion in an anharmonic potential. The condensate follows a well-defined orbital trajectory in a static trap and experiences an effective rotating potential induced by the trap anharmonicity. The sustained geometric squeezing continuously deforms the condensate and drives a self-organized synchronization process, in which the intrinsic rotation gradually locks to the orbital motion. Numerical simulations further reveal the formation of a ring-shaped vortex array over longer timescales, arising from the coherent evolution of the rotating matter wave during the locking dynamics. Our findings establish quantum tidal locking in mesoscopic systems as a robust self-organized mechanism for generating and stabilizing circulating states.

cond-mat.quant-gas↗

arXiv2026

MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning

Clinical practice guidelines (CPGs) encode evidence-based decision logic that clinicians apply by evaluating patient variables, conditional criteria, and recommendation rules. However, existing methods often use CPGs as free-text training data or retrieval sources, underutilizing their procedural decision structure. To better exploit this structure, we introduce a guideline-derived training pipeline that transforms CPG recommendations into executable clinical decision logic and uses it to generate factual and counterfactual question-answering data. Theses data teach models both guideline-supported decisions and how decisions change under different patient conditions. Post-training a medical LLM on the generated data yields MedGuideX. Across four clinical reasoning benchmarks, MedGuideX achieves a 10.28% relative improvement in average accuracy. Physician evaluation further shows that MedGuideX better recovers clinician authored reasoning steps and produces physician-preferred rationales in faithfulness, validity, completeness, and clarity. Overall, our results show that executable decision logic from CPGs can be transformed into scalable supervision for building reliable medical LLMs.

cs.AI↗

arXiv2026

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, and events change over time, models may experience continuous knowledge drift, resulting not only in outdated predictions but also in temporally inconsistent reasoning. Although existing approaches, such as continual finetuning, knowledge editing, and retrieval-augmented generation (RAG), aim to update or supplement model knowledge, they are rarely evaluated in settings that reflect chronological, evolving, and real-world knowledge evolution. In this work, we introduce a new benchmark of real-world dynamic events, constructed from time-stamped evidence that captures how knowledge evolves over time, which enables systematic evaluation of model adaptation under continuous knowledge drift. The benchmark reveals that most existing methods, including vanilla RAG and several learning-based approaches, struggle under this setting, exposing critical limitations such as catastrophic forgetting and temporal inconsistency. To mitigate these limitations, we propose a time-aware retrieval baseline, Chronos, which progressively organizes retrieved evidence into an Event Evolution Graph to enable more temporally consistent understanding in LLMs without additional training. Overall, this work provides a foundation for analyzing and advancing LLM adaptation to continuous knowledge drift in realistic settings.

cs.CL↗

arXiv2026

SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management

Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this setting, we introduce SupChain-Bench, a unified real-world benchmark that assesses both supply chain domain knowledge and long-horizon tool-based orchestration grounded in standard operating procedures (SOPs). Our experiments reveal substantial gaps in execution reliability across models. We further propose SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieving the strongest and most consistent tool-calling performance. Our work establishes a principled benchmark for studying reliable long-horizon orchestration in real-world operational settings and highlights significant room for improvement in LLM-based supply chain agents.

cs.AI↗

arXiv2026

EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation

Electronic Health Records (EHRs) provide rich longitudinal clinical evidence that is central to medical decision-making, motivating the use of retrieval-augmented generation (RAG) to ground large language model (LLM) predictions. However, long-horizon EHRs often exceed LLM context limits, and existing approaches commonly rely on truncation or vanilla retrieval strategies that discard clinically relevant events and temporal dependencies. To address these challenges, we propose EHR-RAG, a retrieval-augmented framework designed for accurate interpretation of long-horizon structured EHR data. EHR-RAG introduces three components tailored to longitudinal clinical prediction tasks: Event- and Time-Aware Hybrid EHR Retrieval to preserve clinical structure and temporal dynamics, Adaptive Iterative Retrieval to progressively refine queries in order to expand broad evidence coverage, and Dual-Path Evidence Retrieval and Reasoning to jointly retrieves and reasons over both factual and counterfactual evidence. Experiments across four long-horizon EHR prediction tasks show that EHR-RAG consistently outperforms the strongest LLM-based baselines, achieving an average Macro-F1 improvement of 10.76%. Overall, our work highlights the potential of retrieval-augmented LLMs to advance clinical prediction on structured EHR data in practice.

cs.AI↗

arXiv2026

TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL

Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large language models on complex reasoning tasks. However, standard GRPO treats each rollout trajectory as an independent flat sequence and assigns a single sequence-level advantage to all tokens, which leads to sample inefficiency and a length bias toward verbose, redundant chains of thought without improving logical depth. We introduce TreeAdv (Tree-Structured Advantage Redistribution for Group-Based RL), which makes the tree structure of group rollouts explicit for both exploration and advantage assignment. Specifically, TreeAdv builds a group of trees (a forest) based on an entropy-driven sampling method where each tree branches at high-uncertainty decisions while sharing low-uncertainty tokens across rollouts. Then, TreeAdv aggregates token-level advantages for internal tree segments by redistributing the advantages of complete rollouts (all leaf nodes), and TreeAdv can easily apply to group-based objectives such as GRPO or GSPO. Across 10 math reasoning benchmarks, TreeAdv consistently outperforms GRPO and GSPO, while using substantially fewer generated tokens under identical supervision, data, and decoding budgets.

cs.LG↗

arXiv2025

Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading

Alpha factor mining is a fundamental task in quantitative trading, aimed at discovering interpretable signals that can predict asset returns beyond systematic market risk. While traditional methods rely on manual formula design or heuristic search with machine learning, recent advances have leveraged Large Language Models (LLMs) for automated factor discovery. However, existing LLM-based alpha mining approaches remain limited in terms of automation, generality, and efficiency. In this paper, we propose Chain-of-Alpha, a novel, simple, yet effective and efficient LLM-based framework for fully automated formulaic alpha mining. Our method features a dual-chain architecture, consisting of a Factor Generation Chain and a Factor Optimization Chain, which iteratively generate, evaluate, and refine candidate alpha factors using only market data, while leveraging backtest feedback and prior optimization knowledge. The two chains work synergistically to enable high-quality alpha discovery without human intervention and offer strong scalability. Extensive experiments on real-world A-share benchmarks demonstrate that Chain-of-Alpha outperforms existing baselines across multiple metrics, presenting a promising direction for LLM-driven quantitative research.

cs.CE↗

arXiv2025

Spin Polarization Control via Magnetic Field in Dissipative Bosonic Systems

Engineering spin polarization in dissipative bosonic systems is crucial for advancing quantum technologies, especially for applications in quantum metrology and space-based quantum simulations. This work demonstrates precise magnetic moment control in multicomponent Bose gases during evaporative cooling via tailored magnetic fields. By adjusting the magnetic field gradients, null point position, and duration, we selectively tune evaporation rates of magnetic sublevels, achieving targeted spin polarization. Theoretical models, validated by numerical simulations and Stern-Gerlach experiments, reveal how magnetic fields reshape trapping potentials and spin-dependent dissipation. The results establish a dissipative spin-selection mechanism governing polarization evolution in evaporatively cooled Bose gases and provide a framework for engineering spin-polarized quantum states.

cond-mat.quant-gas↗

arXiv2025

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning

Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy and rely on uniform length-based rewards that overlook the differing contributions of individual tokens, often harming correctness. We revisit length optimization in RL through the perspective of token significance. Observing that many chain-of-thought (CoT) tokens contribute little to the final answer, we introduce a significance-aware length reward that selectively penalizes insignificance tokens, reducing redundancy while preserving essential reasoning. We also propose a dynamic length reward that encourages more detailed reasoning early in training and gradually shifts toward conciseness as learning progresses. Integrating these components into standard policy optimization yields a framework that improves both reasoning efficiency and accuracy. Experiments across multiple benchmarks demonstrate substantial reductions in response length while preserving or improving correctness, highlighting the importance of modeling token significance for efficient LLM reasoning.

cs.LG↗

arXiv2025

SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards, reinforcement learning struggles to sample successful trajectories, leading to inefficient learning. At the same time, these offline trajectories that represent correct reasoning paths are not utilized by standard on-policy reinforcement learning methods. We introduce SuperRL, a unified training framework that adaptively alternates between RL and SFT. Whenever every rollout for a given instance receives zero reward, indicating the absence of a learning signal, SuperRL falls back to SFT on the curated offline data. Extensive experiments across diverse reasoning benchmarks show that SuperRL surpasses vanilla RL by delivering higher sample efficiency, stronger generalization, and improved robustness under sparse rewards.

cs.AI↗

arXiv2025

Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning

Tables are a fundamental medium for organizing and analyzing data, making table reasoning a critical capability for intelligent systems. Although large language models (LLMs) exhibit strong general reasoning abilities, they still struggle with accurate numerical reasoning over tabular data, particularly in complex table settings beyond simple relational lookup. Spreadsheet formulas provide a powerful and expressive interface for executable symbolic operations, enabling rich reasoning patterns that remain largely underexplored by existing LLMs. In this paper, we introduce Formula-R1, a model trained via Formula Tuning (Fortune), a formula-driven reinforcement learning (RL) framework for table reasoning. Formula Tuning trains LLMs to generate executable spreadsheet formulas for question answering over general tabular data, using execution success and answer correctness as reward signals, thereby reducing reliance on supervised formula annotations. We demonstrate the effectiveness of Formula Tuning through extensive experiments on seven table reasoning benchmarks. It substantially improves LLM performance on table reasoning, particularly for tasks involving complex tables and multi-step numerical computation. Moreover, Formula-R1 consistently outperforms prior methods under controlled comparison settings. Beyond empirical gains, our extensive analyses provide insights into the role of RL in formula-driven table reasoning, highlighting the broader potential of formula-driven RL to enhance reasoning capabilities in LLMs.

cs.AI↗

arXiv2025

More Bang for the Buck: Process Reward Modeling with Entropy-Driven Uncertainty

We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables dynamic, uncertainty-aligned segmentation of complex reasoning steps, eliminating the need for costly manual step annotations. Unlike previous Process Reward Models (PRMs) that rely on static partitioning and human labeling, EDU-PRM automatically anchors step boundaries at tokens with high predictive entropy, effectively capturing intrinsic logical transitions and facilitating efficient exploration of diverse reasoning paths. On the ProcessBench benchmark, EDU-PRM outperforms strong public PRM baselines, such as Math-Shepherd PRM and Omega PRM, and EDU-PRM achieves comparable results with SOTA models while only using 1.5% training data. Furthermore, by leveraging our proposed EDU sampling strategy, we observe accuracy boosts from 64.7% to 67.3% for generative reasoning tasks, accompanied by a reduction of 32% in token usage. These findings underscore the potential of EDU-PRM as a scalable and annotation-efficient paradigm for process supervision in mathematical reasoning, paving the way for more efficient and robust approaches to complex mathematical problem solving.

cs.LG↗

arXiv2025

TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models

Tabular data analysis is crucial in many scenarios, yet efficiently identifying the most relevant data analysis queries and results for a new table remains a significant challenge. The complexity of tabular data, diverse analytical operations, and the demand for high-quality analysis make the process tedious. To address these challenges, we aim to recommend query-code-result triplets tailored for new tables in tabular data analysis workflows. In this paper, we present TablePilot, a pioneering tabular data analysis framework leveraging large language models to autonomously generate comprehensive and superior analytical results without relying on user profiles or prior interactions. The framework incorporates key designs in analysis preparation and analysis optimization to enhance accuracy. Additionally, we propose Rec-Align, a novel method to further improve recommendation quality and better align with human preferences. Experiments on DART, a dataset specifically designed for comprehensive tabular data analysis recommendation, demonstrate the effectiveness of our framework. Based on GPT-4o, the tuned TablePilot achieves 77.0% top-5 recommendation recall. Human evaluations further highlight its effectiveness in optimizing tabular data analysis workflows.

cs.CL↗

arXiv2025

DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely on expensive supervised learning or distillation techniques that require significant computational resources and hand-labeled data. We introduce DeepRetrieval, a reinforcement learning (RL) approach that trains LLMs for query generation through trial and error without supervised data (reference query). Using retrieval metrics as rewards, our system generates queries that maximize retrieval performance. DeepRetrieval outperforms leading methods on literature search with 65.07% (vs. previous SOTA 24.68%) recall for publication search and 63.18% (vs. previous SOTA 32.11%) recall for trial search using real-world search engines. DeepRetrieval also dominates in evidence-seeking retrieval, classic information retrieval and SQL database search. With only 3B parameters, it outperforms industry-leading models like GPT-4o and Claude-3.5-Sonnet on 11/13 datasets. These results demonstrate that our RL approach offers a more efficient and effective paradigm for information retrieval. Our data and code are available at: https://github.com/pat-jj/DeepRetrieval.

cs.IR↗

arXiv2025

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation (RAG) methods provide external information, the lack of explicit organization among retrieved passages limits their effectiveness, leading to brittle reasoning pathways. Recent interpretability studies highlighting the importance of structured intermediate reasoning further align with this perspective. We propose Retrieval-And-Structuring (RAS), a framework that dynamically constructs question-specific knowledge graphs through iterative retrieval and structured knowledge building. RAS interleaves targeted retrieval planning with incremental graph construction, enabling models to assemble and reason over evolving knowledge structures tailored to each query. On seven knowledge-intensive benchmarks, RAS consistently outperforms strong baselines, achieving up to 8.7\% and 7.0\% gains with proprietary and open-source LLMs, respectively. Our results demonstrate that dynamic, question-specific knowledge structuring offers a robust path to improving reasoning accuracy and robustness in language model generation.

cs.CL↗