18 papers
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: (…
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…
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
Zian Liu, Yiwen Hu, Zican Dong +5
Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-context modeling. However, existing context extension approaches typ…
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…
Hyperball May Not Be a Free Lunch
Yihao Xiao, Jialong Sun, Zitian Gao +5
For scale-invariant deep networks, Hyperball-style optimizers have shown strong performance in large-scale training by fixing the norms of matrix-valued parameters and normalizing…
Loop the Loopies!
Zitian Gao, Yilong Chen, Yihao Xiao +4
We present Loopie, the most powerful open-source looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active…
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…
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
Jia Deng, Yimeng Chen, Xiaoqing Xiang +10
Training deep-search agents requires verifiable questions that demand substantial evidence acquisition, yet structurally complex tasks may still admit cheap identifying routes when…
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…
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
Yilong Chen, Yanxi Xie, Zitian Gao +10
Large token-indexed lookup tables provide a compute-decoupled scaling path, but their practical gains are often limited by poor parameter efficiency and rapid memory growth. We att…
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…
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…
Universal Reasoning Model
Zitian Gao, Lynx Chen, Yihao Xiao +5
Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored.…
What Makes Diffusion Language Models Super Data Learners?
Zitian Gao, Haoming Luo, Lynx Chen +4
Recent studies have shown that diffusion language models achieve remarkable data efficiency under limited-data constraints, yet the underlying mechanisms remain unclear. In this wo…