Related papers: Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding

Related papers

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents [83.37969790806069]
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it.<n>We present Agent DebuggerX, an open-source framework that organizes debug as a closed loop of Detect, Attribute, Recover, and Rerun.<n>At its core, Deep Debugger performs multi-turn root-cause diagnosis through global trajectory understanding.
arXiv Detail & Related papers (2026-07-21T06:21:13Z)
CodeAlchemy: Synthetic Code Rewriting at Scale [18.89851727350116]
We present CodeAlchemy, a framework that transforms publicly sourced code into semantically-rich training data.<n>We process 3 corpora across 15 languages to generate 500B+ tokens of synthetic data plus 350B reasoning tokens.<n>CodeTrace executes 1.3M+ files across 14 languages and 5K libraries, capturing control flow, state tracking, and library knowledge.
arXiv Detail & Related papers (2026-06-08T19:15:27Z)
ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking [2.2573512203799626]
We propose ReacTOD, a bounded neuro-symbolic architecture that reformulates NLU as discrete tool calls within a self-correcting ReAct loop governed by deterministic validation.<n>A bounded ReAct loop enables iterative self-correction, improving accuracy by up to 9.3 percentage points over single-pass inference on MultiWOZ.
arXiv Detail & Related papers (2026-05-18T20:06:04Z)
Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory [0.7723674433972977]
We introduce Chronos, a temporal-aware memory framework for conversational AI.<n> Chronos decomposes raw dialogue into subject-verb-object events with resolved datetime ranges and entity aliases.<n>At query time, Chronos applies dynamic prompting to generate tailored retrieval guidance for each question.
arXiv Detail & Related papers (2026-03-17T17:59:20Z)
AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms [54.99368693313797]
Existing benchmarks test only individual languages/tools, so the performance numbers are not directly comparable.<n>We address this gap with AlgoVeri, a benchmark that evaluates vericoding of $77$ classical algorithms in Dafny, Verus, and Lean.
arXiv Detail & Related papers (2026-02-10T06:58:26Z)
Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling [13.419095400140913]
textbfChronos is a chronological reasoning scorer that models each trajectory as a time series.<n>Chronos consistently delivers substantial gains across a variety of models, with negligible computational overhead.
arXiv Detail & Related papers (2026-02-01T12:57:36Z)
SwiftSolve: A Self-Iterative, Complexity-Aware Multi-Agent Framework for Competitive Programming [4.611794255231338]
We present Swift, a complexity-aware multi-agent system for competitive programming.<n>We show that profiling and complexity-guided replanning reduce inefficiency while preserving accuracy.
arXiv Detail & Related papers (2025-10-26T11:05:27Z)
Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality [4.05144752916486]
Large Language Models (LLMs) are becoming integral to modern software development.<n>We leverage CodeChat, a dataset of 82,845 real-world developer-LLM conversations.<n>We find that LLM responses are substantially longer than developer prompts.
arXiv Detail & Related papers (2025-09-12T16:52:49Z)
A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback [30.446511584123492]
Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored.<n>We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions.<n>We synthesize and evolve 2,021 code tasks sourced from 14 programming languages, supporting multi-turn evaluation through feedback-driven task variants.
arXiv Detail & Related papers (2025-07-01T11:51:40Z)
SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
arXiv Detail & Related papers (2025-05-29T18:28:02Z)
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory [52.44029486173232]
Dynamic Cheatsheet (DC) is a lightweight framework that endows a black-box language model with a persistent, evolving memory.<n>DC enables models to store and reuse accumulated strategies, code snippets, and general problem-solving insights at inference time.<n>This test-time learning enhances performance substantially across a range of tasks without needing explicit ground-truth labels or human feedback.
arXiv Detail & Related papers (2025-04-10T17:57:33Z)
LocAgent: Graph-Guided LLM Agents for Code Localization [25.395102705800916]
LocAgent is a framework that addresses code localization through graph-based representation.<n>Our method with the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves comparable results to SOTA proprietary models at greatly reduced cost.
arXiv Detail & Related papers (2025-03-12T05:55:01Z)
MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings [2.1262605464247812]
Self-Distillation is a principled approach to trading inference cost for accuracy across various code understanding tasks.<n>Our architecture improves text-to-code and code-to-code search by targeting specific encoder layers as exit heads.<n>We release a new dataset created through code translation that extends text-to-code benchmarks with cross-language code-to-code pairs.
arXiv Detail & Related papers (2025-03-04T21:08:17Z)
CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification [71.34070740261072]
This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases.<n>The benchmark is containerized for code execution across tasks, and we will release the code, data, and construction methodologies.
arXiv Detail & Related papers (2025-02-12T21:42:56Z)
Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraph [1.4582633500696451]
The proposed system integrates three core components LangGraph, GLM4 Flash, and ChromaDB within a four step iterative workflow to deliver robust performance and functionality seamless.<n>LangGraph serves as a graph-based library for orchestrating tasks, providing precise control and execution while maintaining a unified state object for dynamic updates and consistency.<n>GLM4 Flash, a large language model, leverages its advanced capabilities in natural language understanding, contextual reasoning, and multilingual support to generate accurate code snippets based on user prompts.
arXiv Detail & Related papers (2025-01-29T12:01:00Z)
Token-by-Token Regeneration and Domain Biases: A Benchmark of LLMs on Advanced Mathematical Problem-Solving [0.0]
This study evalu-ates 10 large language models (LLMs) with 7 to 8 billion parameters using the MATH dataset.<n>The focus is on their ability to generate executable Python code as a step in their reasoning process, involving over 9,450 code executions.
arXiv Detail & Related papers (2025-01-28T17:11:36Z)
VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning [10.70881967278009]
We introduce VisualCoder, a simple yet effective approach that enhances code reasoning by integrating multimodal Chain-of-Thought snippets (CoT) reasoning with a visual Control Flow Graph (CFG)<n>We address challenges in multimodal CoT integration through a reference mechanism, ensuring consistency between code and its execution path, thereby improving performance in program behavior prediction, error detection, and output generation.
arXiv Detail & Related papers (2024-10-30T19:07:01Z)
Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
arXiv Detail & Related papers (2024-10-02T09:11:10Z)
Chronos: Learning the Language of Time Series [79.38691251254173]
Chronos is a framework for pretrained probabilistic time series models. We show that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks.
arXiv Detail & Related papers (2024-03-12T16:53:54Z)
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution [36.30158138035512]
We present a benchmark consisting of 800 Python functions (3-13 lines) Each function comes with an input-output pair, leading to two natural tasks: input prediction and output prediction. We show that simple CoT and fine-tuning schemes can improve performance on our benchmark but remain far from solving it.
arXiv Detail & Related papers (2024-01-05T20:53:51Z)
QLoRA: Efficient Finetuning of Quantized LLMs [66.58009990713134]
We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU. QLoRA backpropagates through a frozen, 4-bit quantized pretrained language model into Low Rank Adapters(LoRA) Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark.
arXiv Detail & Related papers (2023-05-23T17:50:33Z)
Progressive-Hint Prompting Improves Reasoning in Large Language Models [63.98629132836499]
This paper proposes a new prompting method, named Progressive-Hint Prompting (PHP) It enables automatic multiple interactions between users and Large Language Models (LLMs) by using previously generated answers as hints to progressively guide toward the correct answers. We conducted extensive and comprehensive experiments on seven benchmarks. The results show that PHP significantly improves accuracy while remaining highly efficient.
arXiv Detail & Related papers (2023-04-19T16:29:48Z)
ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
arXiv Detail & Related papers (2022-03-15T08:25:08Z)
DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons [5.564793925574796]
We present an approach to automated debug using large, pretrained transformers. We start by training a bug-creation model on reversed commit data for the purpose of generating synthetic bugs. Next, we focus on 10K repositories for which we can execute tests, and create buggy versions of all functions that are covered by passing tests.
arXiv Detail & Related papers (2021-05-19T18:40:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.