arXiv subjects

Dingzirui Wang

Publications and source records attributed to Dingzirui Wang.

At least 19 recordsLinked to original sources

arXiv2026

FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models

Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research, yet existing benchmarks remain far from realistic research settings. We introduce \ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research. \ourbenchmark contains $143$ instances drawn from papers accepted to STOC, FOCS, SODA, and COLT in 2025-2026, preserving paper-specific definitions, assumptions, and proof dependencies, with expert-verified Lean formalizations and proofs. Evaluations of leading LLMs reveal that current models remain far from reliably completing the full research pipeline. In particular, autoformalization is the sharpest bottleneck: the best model achieves only $11.5$ on translating natural-language claims into formal theorem statements, compared with $28.6$ Pass@8 when proving human-provided formal statements. Building on \ourbenchmark, we further develop an automated TCS research framework that generates, formalizes, filters, and proves new claims. Of $64$ generated claims, only $6$ ultimately pass expert evaluation and proof verification, indicating that beyond formalization, limited research taste remains another major barrier to autonomous TCS research.

cs.CL↗

arXiv2026

CurateEvo: Data-Curation Evolving for Agentic Post-Training

Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures. We propose CurateEvo, a failure-driven dynamic evolution framework for agentic post-training data curation. CurateEvo represents the curation strategy as executable code and iteratively rewrites it using failed trajectories from a held-out development set. At each epoch, the evolved strategy transforms a fixed raw corpus into supervised fine-tuning data, reinforcement learning data, and an inference-time memory bank. The evolution process first improves effectiveness by diagnosing recurring failure modes and augmenting, filtering, or refining data accordingly, and then improves efficiency by pruning redundant or low-utility training turns under a cost-aware objective. Experiments on ACEBench-Agent, BFCL-V4, and τ^2-Bench under both labeled and wild-data settings show that CurateEvo consistently outperforms prior curation methods, improving average scores by 3.2 and 2.7 points, respectively. Further analyses demonstrate that CurateEvo is compatible with different post-training recipes and substantially reduces curation overhead.

cs.CL↗

arXiv2026

Scaling Laws for Agent Harnesses via Effective Feedback Compute

Agent harnesses shape language-model performance by controlling tool use, feedback, verification, memory, and repair. Yet raw test-time expenditure, such as tokens, tool calls, wall time, or cost, cannot distinguish useful feedback from redundant or unstable interaction. We introduce \emph{Effective Feedback Compute} (EFC), a trace-level scaling coordinate for informative, valid, non-redundant, and retained feedback. We further define Estimated-EFC, NRS-EFC, harness efficiency $η$, and task-demand normalization for realistic traces and heterogeneous tasks. Across synthetic, real, held-out, and prospective evaluations, EFC-based coordinates outperform raw-compute baselines and SAS. Oracle-EFC/$D_{\mathrm{task}}$ reaches $R^2=0.99$ in controlled scaling, and NRS-EFC/$D_{\mathrm{task}}$ reaches $R^2=0.93$ on real traces where raw compute has near-zero or negative fit. Finally, \ours uses EFC as a companion control layer for existing harnesses, improving mean pass rate from $61.2\%$ to $68.2\%$ while reducing mean raw cost from $213.8$ to $85.1$ under matched settings. These results suggest that harness scaling depends on durable, task-sufficient feedback rather than raw computation alone.

cs.CL↗

arXiv2026

SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL

Text-to-SQL aims to convert natural language questions into executable SQL queries. While memory-based agent system improves complex SQL generation, existing memory design neglect historical experience and suffer from weak structure analysis, shallow semantic understanding, and poor schema alignment. To address these challenges, we propose SDAM. Specifically, SDAM identifies potential errors via a structure-difference aware reasoning tree, extracts deep semantic rules through contradiction-aware reflection, and enhances structural consistency using a schema-grounded memory evolution mechanism to bind memory with database schemas. We integrate SDAM into a Text-to-SQL framework named SDAM-SQL. Experiment shows that SDAM-SQL achieves 2.0 and 0.4 improvement on BIRD-dev and Spider-test compared with mainstream Text-to-SQL methods, showing the effectiveness of SDAM-SQL.

cs.CL↗

arXiv2026

AlignEvoSkill: Towards Knowledge-Aware and Task-Aligned Agent Skill Evolution

Reusable skills play a key role in improving LLM-based agents, but existing skill-evolution methods often fail to ensure that evolved skills both cover the knowledge required by the task and remain aligned with the target task. As a result, evolved skills could be incomplete or irrelevant. To address this limitation, we propose AlignEvoSkill, a skill-evolution framework that jointly models knowledge coverage and task alignment. Given failed task trajectories, AlignEvoSkill first identifies task-relevant knowledge tags, retrieves complementary prior skills, and adapts them into candidate skills that address missing knowledge. It then selects high-quality candidates using a joint filtering criterion based on knowledge-coverage and task-alignment scores. Experiments on 3 benchmarks with4 LLM backbones show a 34.7% relative gain of AlignEvoSkill over the non-evolution baseline and achieves a new SOTA in skill evolution with lower cost.

cs.CL↗

arXiv2026

When Does Context Help? Error Dynamics of Contextual Information in Large Language Models

Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly understood beyond specific settings such as in-context learning (ICL). We present a unified theoretical framework for analyzing the effect of arbitrary contextual information in Transformer-based LLMs. Our analysis characterizes contextual influence through output error dynamics. In a single-layer Transformer, we prove that the context-conditioned error vector decomposes additively into the baseline error vector and a contextual correction vector. This yields necessary geometric conditions for error reduction: the contextual correction must align with the negative baseline error and satisfy a norm constraint. We further show that the contextual correction norm admits an explicit upper bound determined by context-query relevance and complementarity. These results extend to multi-context and multi-layer Transformers. Experiments across ICL, retrieval-augmented generation, and memory evolution validate our theory and motivate a principled context selection strategy that improves performance by $0.6\%$.

cs.CL↗

arXiv2026

How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location

While Large Language Models (LLMs) are increasingly deployed for table-related tasks, the internal mechanisms enabling them to process linearized two-dimensional structured tables remain opaque. In this work, we investigate the process of table understanding by dissecting the atomic task of cell location. Through activation patching and complementary interpretability techniques, we delineate the table understanding mechanism into a sequential three-stage pipeline: Semantic Binding, Coordinate Localization, and Information Extraction. We demonstrate that models locate the target cell via an ordinal mechanism that counts discrete delimiters to resolve coordinates. Furthermore, column indices are encoded within a linear subspace that allows for precise steering of model focus through vector arithmetic. Finally, we reveal that models generalize to multi-cell location tasks by multiplexing the identical attention heads identified during atomic location. Our findings provide a comprehensive explanation of table understanding within Transformer architectures.

cs.CL↗

arXiv2025

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond

Existing research indicates that the output of Chain-of-Thought (CoT) is significantly affected by input perturbations. Although many methods aim to mitigate such impact by optimizing prompts, a theoretical explanation of how these perturbations influence CoT outputs remains an open area of research. This gap limits our in-depth understanding of how input perturbations propagate during the reasoning process and hinders further improvements in prompt optimization methods. Therefore, in this paper, we theoretically analyze the effect of input perturbations on the fluctuation of CoT outputs. We first derive an upper bound for input perturbations under the condition that the output fluctuation is within an acceptable range, based on which we prove that: (i) This upper bound is positively correlated with the number of reasoning steps in the CoT; (ii) Even an infinitely long reasoning process cannot eliminate the impact of input perturbations. We then apply these conclusions to the Linear Self-Attention (LSA) model, which can be viewed as a simplified version of the Transformer. For the LSA model, we prove that the upper bound for input perturbation is negatively correlated with the norms of the input embedding and hidden state vectors. To validate this theoretical analysis, we conduct experiments on three mainstream datasets and four mainstream models. The experimental results align with our theoretical analysis, empirically demonstrating the correctness of our findings.

cs.CL↗

arXiv2025

Multi-Layer Attention is the Amplifier of Demonstration Effectiveness

Numerous studies have investigated the underlying mechanisms of in-context learning (ICL) effectiveness to inspire the design of related methods. However, existing work predominantly assumes the effectiveness of the demonstrations provided within ICL, while many research indicates that not all demonstrations are effective, failing to yielding any performance improvement during ICL. Therefore, in this paper, we investigate the reasons behind demonstration ineffectiveness. Our analysis is based on gradient flow and linear self-attention models. By setting the gradient flow to zero, we deduce that a demonstration becomes ineffective if its information has either been learned by the model or is irrelevant to the user query. Furthermore, we demonstrate that in multi-layer models, the disparity in effectiveness among demonstrations is amplified with layer increasing, causing the model to focus more on effective ones. Considering that current demonstration selection methods primarily focus on the relevance to the user query while overlooking the information that the model has already assimilated, we propose a novel method called GradS, which leverages gradient flow for demonstration selection. We use the magnitude of the gradient flow of the demonstration with respect to a given user query as the criterion, thereby ensuring the effectiveness of the chosen ones. We validate our derivation and GradS on four prominent LLMs across five mainstream datasets. The experimental results confirm that the disparity in effectiveness among demonstrations is magnified as the model layer increases, substantiating our derivations. Moreover, GradS achieves a relative improvement of $6.8\%$ on average over the strongest baselines, demonstrating its effectiveness.

cs.CL↗

arXiv2025

Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format

Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning formats outperform a single format when generating multiple answers. However, previous works using multiple formats rely on formats labeled by humans, which could be unsuitable for all tasks and have high labeling costs. To address this issue, we adapt suitable formats to the given tasks by generating and selecting formats. We first propose how to measure the reasoning error when generating multiple answers. Then, we introduce Format-Adapter, which utilizes LLMs to generate and select suitable reasoning formats by minimizing the error measurement we present. We conduct experiments on math and commonsense reasoning tasks, where Format-Adapter achieves a 4.3% performance improvement on average over previous works, demonstrating the effectiveness.

cs.CL↗

arXiv2025

RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals

The table reasoning task, crucial for efficient data acquisition, aims to answer questions based on the given table. Recently, reasoning large language models (RLLMs) with Long Chain-of-Thought (Long CoT) significantly enhance reasoning capabilities, leading to brilliant performance on table reasoning. However, Long CoT suffers from high cost for training and exhibits low reliability due to table content hallucinations. Therefore, we propose Row-of-Thought (RoT), which performs iteratively row-wise table traversal, allowing for reasoning extension and reflection-based refinement at each traversal. Scaling reasoning length by row-wise traversal and leveraging reflection capabilities of LLMs, RoT is training-free. The sequential traversal encourages greater attention to the table, thus reducing hallucinations. Experiments show that RoT, using non-reasoning models, outperforms RLLMs by an average of 4.3%, and achieves state-of-the-art results on WikiTableQuestions and TableBench with comparable models, proving its effectiveness. Also, RoT outperforms Long CoT with fewer reasoning tokens, indicating higher efficiency.

cs.CL↗

arXiv2025

Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval

The existing text-to-SQL systems have made significant progress in SQL query generation, but they still face numerous challenges. Existing systems often lack retrieval capabilities for open-domain databases, requiring users to manually filter relevant databases. Additionally, their cross-domain transferability is limited, making it challenging to accommodate diverse query requirements. To address these issues, we propose Abacus-SQL. Abacus-SQL utilizes database retrieval technology to accurately locate the required databases in an open-domain database environment. It also enhances the system cross-domain transfer ability through data augmentation methods. Moreover, Abacus-SQL employs Pre-SQL and Self-debug methods, thereby enhancing the accuracy of SQL queries. Experimental results demonstrate that Abacus-SQL performs excellently in multi-turn text-to-SQL tasks, effectively validating the approach's effectiveness. Abacus-SQL is publicly accessible at https://huozi.8wss.com/abacus-sql/.

cs.CL↗

arXiv2025

MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering

Question answering on the hybrid context of tables and text (TATQA) is a critical task, with broad applications in data-intensive domains. However, existing TATQA datasets are limited to English, leading to several drawbacks: (i) They overlook the challenges of multilingual TAT-QA and cannot assess model performance in the multilingual setting. (ii) They do not reflect real-world scenarios where tables and texts frequently appear in non-English languages. To address the limitations, we propose the first multilingual TATQA dataset (MULTITAT). Specifically, we sample data from 3 mainstream TATQA datasets and translate it into 10 diverse languages. To align the model TATQA capabilities in English with other languages, we develop a baseline, Ours. Experimental results reveal that the performance on non-English data in MULTITAT drops by an average of 19.4% compared to English, proving the necessity of MULTITAT. We further analyze the reasons for this performance gap. Furthermore, Ours outperforms other baselines by an average of 3.3, demonstrating its effectiveness.

cs.CL↗

arXiv2024

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits

The Myers-Briggs Type Indicator (MBTI) is one of the most influential personality theories reflecting individual differences in thinking, feeling, and behaving. MBTI personality detection has garnered considerable research interest and has evolved significantly over the years. However, this task tends to be overly optimistic, as it currently does not align well with the natural distribution of population personality traits. Specifically, (1) the self-reported labels in existing datasets result in incorrect labeling issues, and (2) the hard labels fail to capture the full range of population personality distributions. In this paper, we optimize the task by constructing MBTIBench, the first manually annotated high-quality MBTI personality detection dataset with soft labels, under the guidance of psychologists. As for the first challenge, MBTIBench effectively solves the incorrect labeling issues, which account for 29.58% of the data. As for the second challenge, we estimate soft labels by deriving the polarity tendency of samples. The obtained soft labels confirm that there are more people with non-extreme personality traits. Experimental results not only highlight the polarized predictions and biases in LLMs as key directions for future research, but also confirm that soft labels can provide more benefits to other psychological tasks than hard labels. The code and data are available at https://github.com/Personality-NLP/MbtiBench.

cs.CL↗

arXiv2024

SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types

Scientific question answering (SQA) is an important task aimed at answering questions based on papers. However, current SQA datasets have limited reasoning types and neglect the relevance between tables and text, creating a significant gap with real scenarios. To address these challenges, we propose a QA benchmark for scientific tables and text with diverse reasoning types (SciTaT). To cover more reasoning types, we summarize various reasoning types from real-world questions. To involve both tables and text, we require the questions to incorporate tables and text as much as possible. Based on SciTaT, we propose a strong baseline (CaR), which combines various reasoning methods to address different reasoning types and process tables and text at the same time. CaR brings average improvements of 12.9% over other baselines on SciTaT, validating its effectiveness. Error analysis reveals the challenges of SciTaT, such as complex numerical calculations and domain knowledge.

cs.CL↗

arXiv2024

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks

In-context learning (ICL) is an effective approach to help large language models (LLMs) adapt to various tasks by providing demonstrations of the target task. Considering the high cost of labeling demonstrations, many methods propose synthesizing demonstrations from scratch using LLMs. However, the quality of the demonstrations synthesized from scratch is limited by the capabilities and knowledge of LLMs. To address this, inspired by transfer learning, we propose In-Context Transfer Learning (ICTL), which synthesizes target task demonstrations by transferring labeled demonstrations from similar source tasks. ICTL consists of two steps: source sampling and target transfer. First, we define an optimization objective, which minimizes transfer error to sample source demonstrations similar to the target task. Then, we employ LLMs to transfer the sampled source demonstrations to the target task, matching the definition and format of the target task. Experiments on Super-NI show that ICTL outperforms synthesis from scratch by 2.0% on average, demonstrating the effectiveness of our method.

cs.CL↗

arXiv2024

MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL

The open-domain text-to-SQL task aims to retrieve question-relevant tables from massive databases and generate SQL. However, the performance of current methods is constrained by single-hop retrieval, and existing multi-hop retrieval of open-domain question answering is not directly applicable due to the tendency to retrieve tables similar to the retrieved ones but irrelevant to the question. Since the questions in text-to-SQL usually contain all required information, while previous multi-hop retrieval supplements the questions with retrieved documents. Therefore, we propose the multi-hop table retrieval with removal (MURRE), which removes previously retrieved information from the question to guide the retriever towards unretrieved relevant tables. Our experiments on two open-domain text-to-SQL datasets demonstrate an average improvement of 5.7% over the previous state-of-the-art results.

cs.CL↗

arXiv2024

DAC: Decomposed Automation Correction for Text-to-SQL

Text-to-SQL is an important task that helps people obtain information from databases by automatically generating SQL queries. Considering the brilliant performance, approaches based on Large Language Models (LLMs) become the mainstream for text-to-SQL. Among these approaches, automated correction is an effective approach that further enhances performance by correcting the mistakes in the generated results. The existing correction methods require LLMs to directly correct with generated SQL, while previous research shows that LLMs do not know how to detect mistakes, leading to poor performance. Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance. We first demonstrate that decomposed correction outperforms direct correction since detecting and fixing mistakes with the results of the decomposed sub-tasks is easier than with SQL. Based on this analysis, we introduce Decomposed Automation Correction (DAC), which corrects SQL by decomposing text-to-SQL into entity linking and skeleton parsing. DAC first generates the entity and skeleton corresponding to the question and then compares the differences between the initial SQL and the generated entities and skeleton as feedback for correction. Experimental results show that our method improves performance by $3.7\%$ on average of Spider, Bird, and KaggleDBQA compared with the baseline method, demonstrating the effectiveness of DAC.

cs.CL↗