21 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…
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
A. Jian Yang, An Huang, Bo Dan +173
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (…
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…
CARAT: Do Materials LLMs Reason or Recite?
Jiajun Wu, Jian Yang, Zixiang Ni +2
When a materials LLM answers a question about crystal structure, does it reason from the structure or copy an answer already printed in its input? Accuracy cannot tell: a structura…
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.,…
WebWorld: The Browser as a World Model for Self-Improving Web Code
Jiajun Wu, Jian Yang, Yaxin Du +7
VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility under that judge is a poor pr…
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
Zhaoyi Li, Deyang Kong, Yuan Wei +13
On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly unders…
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through compl…
Agentic evolution of physically constrained foundation models
Jiangwei Zhang, Wen Sun, Chong Wang +7
Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatib…
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jian Yang, Shawn Guo, Wei Zhang +16
Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count. Parallel loop T…
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
George Wu, Nan Jing, Qing Yi +7
Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation during inference. Recent struct…
ClawGym: A Scalable Framework for Building Effective Claw Agents
Fei Bai, Huatong Song, Shuang Sun +11
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains const…
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
He Du, Qiming Ge, Jiakai Hu +18
We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented…
From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation
Chuang Peng, Wei Zhang, Renshuai Tao +2
Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy and heterogeneous nature of re…
Ensemble-Based Uncertainty Estimation for Code Correctness Estimation
Yunxiang Wei, Tianlin Li, Yuwei Zheng +6
Large language models (LLMs) have demonstrated remarkable capabilities in generating programs from natural language descriptions, yet ensuring their correctness without an external…
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…
Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization
Fei Bai, Zhipeng Chen, Chuan Hao +6
Recently, reinforcement learning~(RL) has become an important approach for improving the capabilities of large language models~(LLMs). In particular, reinforcement learning from ve…
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…
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…
Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing
Yuwen Li, Wei Zhang, Zelong Huang +8
Enabling Large Language Models (LLMs) to reliably invoke external tools remains a critical bottleneck for autonomous agents. Existing approaches suffer from three fundamental chall…
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…