20 papers
ProductWebBench: Evaluating Website Continuity Beyond Task Completion
Jiajun Wu, Jian Yang, Yaxin Du +9
Frontend coding agents are usually graded on one question: did the requested target get built. Real engineering changes carry a second obligation, because the rest of the site has…
When Can LLM Reasoning Reliably Reuse Intermediate Results?
Deyuan Liu, Zecheng Wang, Xuanyi Liu +5
Sampling complete solutions gives large language models more chances to solve a problem, but each attempt starts again. For tasks with several subproblems, all required answers mus…
RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents
Yunqi Liu, Peiyu Wang, Bingli Wang +21
Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or eva…
AutoDataBench: A Data-centric Testbed for Accelerating Auto Research
Ruifeng Yuan, Yizhi Li, Yaxin Du +9
Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and data, making it difficult to…
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Siwei Wu, Jincheng Ren, Yizhi Li +12
Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience.…
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo +10
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention, with closed-source LLMs (e.g.,…
HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents
Yaxin Du, Yifan Zhou, Yujie Ge +7
Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates…
Automated Conjecture Resolution with Formal Verification
Haocheng Ju, Guoxiong Gao, Jiedong Jiang +13
Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capa…
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
Guoxiong Gao, Zeming Sun, Jiedong Jiang +5
Proving theorems in Lean 4 often requires identifying a scattered set of library lemmas whose joint use enables a concise proof -- a task we call global premise retrieval. Existing…
Matlas: A Semantic Search Engine for Mathematics
Haocheng Ju, Leheng Chen, Peihao Wu +2
Retrieving mathematical knowledge is a central task in both human-driven research, such as determining whether a result already exists, finding related results, and identifying his…
InCoder-32B-Thinking: Industrial Code World Model for Thinking
Jian Yang, Wei Zhang, Jiajun Wu +22
Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason about hardware constraints and…
InCoder-32B: Code Foundation Model for Industrial Scenarios
Jian Yang, Wei Zhang, Jiajun Wu +25
Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios tha…
IQuest-Coder-V1 Technical Report
Jian Yang, Wei Zhang, Shawn Guo +35
In this report, we introduce the IQuest-Coder-V1 series-(7B/14B/40B/40B-Loop), a new family of code large language models (LLMs). Moving beyond static code representations, we prop…
CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
Yicheng He, Zheng Zhao, Zhou Kaiyu +3
Current paradigms for code verification rely heavily on external mechanisms-such as execution-based unit tests or auxiliary LLM judges-which are often labor-intensive or limited by…
Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
Siwei Wu, Yizhi Li, Yuyang Song +8
Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. H…
AGRO-SQL: Agentic Group-Relative Optimization with High-Fidelity Data Synthesis
Cehua Yang, Dongyu Xiao, Junming Lin +7
The advancement of Text-to-SQL systems is currently hindered by the scarcity of high-quality training data and the limited reasoning capabilities of models in complex scenarios. In…
M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation
Fanglin Xu, Wei Zhang, Jian Yang +5
The rapid advancement of code large language models (LLMs) has sparked significant research interest in systematically evaluating their code generation capabilities, yet existing b…
Context as a Tool: Context Management for Long-Horizon SWE-Agents
Shukai Liu, Jian Yang, Bo Jiang +4
Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scal…
Scaling Laws for Code: Every Programming Language Matters
Jian Yang, Shawn Guo, Lin Jing +8
Code large language models (Code LLMs) are powerful but costly to train, with scaling laws predicting performance from model size, data, and compute. However, different programming…
REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning
Ziju Shen, Naohao Huang, Fanyi Yang +11
Nowadays, formal theorem provers have made monumental progress on high-school and competition-level mathematics, but few of them generalize to more advanced mathematics. In this pa…