Skip to content
Papers.

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents research paper by Alibaba (Qwen), 2026

Alibaba (Qwen) · Sep 20, 2026 · Training and scaling · 0 citations · 48 upvotes · unverified

Read on arXiv

What it shows

Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with regressions in...

UnverifiedHugging Face's summary; not yet checked by hand.

More from Alibaba (Qwen)

All 61
PaperCitations
HappyWorld-BenchEvaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, interaction, and modification.Agents and evaluation · Sep 2026 · Unverified0
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual DialogueWe define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model.Multimodal and robotics · Sep 2026 · Unverified0
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use AgentsComputer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line.Agents and evaluation · Sep 2026 · Unverified0
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker DistillationCORE distills compositional ranking judgments from a cross-attentive reranker into an embedding model via synthesized multi-level candidates and a Rank-KL objective, improving compositional retrieval without degrading standard performance.Reasoning · Sep 2026 · Unverified0
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal EnvironmentsTerminal-Universe reconstructs executable workspaces from agent trajectories to synthesize diverse training tasks and improves post-training performance through supervised fine-tuning.Agents and evaluation · Sep 2026 · Unverified1
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous DrivingQwen-Drive-1.0 is a vision-language foundation model for autonomous driving that unifies 3D perception, visual question answering, and motion planning via shared representations and staged training.Multimodal and robotics · Aug 2026 · Unverified3
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training StabilityQwen3.8-Flash-Next: a 125B mixture-of-experts model with 6B active that nearly matches its 397B predecessor at 1/9 the training compute.Architectures · Aug 20266
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic ManipulationDreamX-Phi 1.0 is an action-conditioned video world model for robotic manipulation that uses geometric attention encoding, depth estimation, object masks with a frozen teacher, and distillation to generate faithful future observations.Multimodal and robotics · Aug 2026 · Unverified2

Other training and scaling papers

Topic
PaperCitations
LoRA: Low-Rank Adaptation of Large Language ModelsLoRA fine-tunes a large model by training small low-rank matrices, cutting trainable parameters by 10,000 times.Microsoft · Jun 202123.3k
Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.OpenAI · Jan 20209,065
Training Compute-Optimal Large Language ModelsChinchilla: for a fixed compute budget, train a smaller model on more data; parameters and tokens should grow together.Google DeepMind · Mar 20223,756
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model ParallelismMegatron-LM splits each Transformer layer across GPUs to train models with billions of parameters.NVIDIA · Sep 20193,179
DeepSeek LLM: Scaling Open-Source Language Models with LongtermismDeepSeek LLM, an open-source language model project, develops a large dataset and employs SFT and DPO to achieve performance surpassing LLaMA-2 70B and GPT-3.5 in various benchmarks and open-ended evaluations.DeepSeek · Jan 2024 · Unverified855
LoRA Learns Less and Forgets LessLoRA learns less than full fine-tuning on code and math, but forgets less of what the model already knew.Databricks · May 2024407
About this paper
Authors
Jie Zhao, Ziyu Jiang, Suhang Zheng and 3 more
arXiv
2609.23377 · PDF
Citations
0, 0 influential · Semantic Scholar
Upvotes
48 · Hugging Face
Code
github.com/alibaba/AgenticBigBang
Lab
Alibaba (Qwen) · on Companies · on Quarterly

Changes

What changed
Influential citationsfirst count: 0Sep 25, 2026
Citationsfirst count: 0Sep 25, 2026
New paperFound by the weekly scan, unverifiedSep 25, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.