6arXiv cs.CL (Computation and Language)·
Nanbeige4.2-3B: A 3B-parameter agentic model outperforming 9B–12B models on agentic benchmarks
Researchers present Nanbeige4.2-3B, a 3-billion non-embedding parameter model designed for agentic tasks including code-agent, office-agent, and complex tool use. The model is pretrained on 28T tokens using a Looped Transformer architecture that reuses layer stacks to increase capacity without adding parameters, and trained with a multi-stage RL pipeline combining mixed-mode RLHF, length-controlled reasoning RL, and agentic RL with outcome and process rewards. Evaluations claim Nanbeige4.2-3B outperforms larger models including Qwen3.5-9B and Gemma4-12B on diverse agentic benchmarks while remaining competitive on reasoning tasks. The result contributes to the ongoing question of how much agentic capability can be packed into compact, locally-deployable models.
Related guides (4)
Agent and Tool EcosystemTopic guide
Agent and Tool Ecosystem: How AI Tooling Is Consolidating Around Agentic Workflows
Read asIn-depth
Related events (8)
Agents-A1: 35B MoE agent matches trillion-parameter models via horizon scaling
Researchers introduce Agents-A1, a 35B Mixture-of-Experts model that claims to match or exceed trillion-parameter models like Kimi-K2 and DeepSeek V4 on long-horizon agentic benchmarks. The approach scales agent trajectory length (averaging 45K tokens) and heterogeneous agent abilities rather than raw parameter count, using a three-stage training recipe including multi-teacher domain-routed distillation. On benchmarks such as SEAL-0, IFBench, HiPhO, and FrontierScience-Olympiad, Agents-A1 achieves leading or competitive results against models with roughly 30x more parameters. The work proposes a practical efficiency path for agentic capability scaling without proportional compute scaling.
Mach-Mind-4-Flash: 35B MoE agentic model matching 100B-class performance via post-training optimization
Mach-Mind-4-Flash is a 35B-parameter Mixture-of-Experts model with only 3B activated parameters that achieves performance comparable to 100B-class models through post-training techniques alone. The pipeline combines a unified RL/OPD training infrastructure with multi-teacher scheduling, parallel domain-specific RL experts fused via Multi-Teacher On-Policy Distillation (MOPD), and Hybrid Median-length Policy Optimization (HMPO) which compresses reasoning chains 19-46% with minimal accuracy loss. Benchmark results include 92.70 on AIME'26, 82.82 on IFBench, and 75.80 on BFCL-v4, claiming to lead or match models 10-30x its activated size at a fraction of inference cost. The work is notable for demonstrating that post-training optimization can close large gaps in activated parameter count for agentic tasks.
Tmax: Open RL training recipe for terminal-using agents achieves 27% on Terminal-Bench 2.0 with 9B parameters
Researchers present Tmax, an open RL training recipe for terminal-using language model agents, achieving 27% on Terminal-Bench 2.0 with a 9B parameter model while outperforming larger models from prior work. The recipe combines a novel data generation taxonomy using difficulty control, personas, and verifier diversification to produce a terminal environment dataset over 2.5x larger than previously released datasets. Training uses a simple outcome-only RL approach, and the authors release data, models, and code to lower the barrier for academic research on terminal agents.
Qwen-AgentWorld: Language world models for general agent simulation and planning
Alibaba's Qwen team introduces Qwen-AgentWorld, a pair of language world models (35B-A3B and 397B-A17B) trained to simulate agentic environments across 7 domains using over 10M interaction trajectories. The models are trained via a three-stage pipeline (CPT, SFT, RL) and evaluated on AgentWorldBench, a new benchmark constructed from 5 frontier models across 9 established benchmarks. Beyond simulation, the work demonstrates two downstream use cases: using the world model as a decoupled RL training environment and as a warm-up for agent foundation models, both yielding gains over baselines.
Qwen3-Coder: 480B MoE Agentic Coding Model Released by Alibaba/Qwen Team
Alibaba's Qwen team has released Qwen3-Coder, a family of code-focused models with the flagship variant being Qwen3-Coder-480B-A35B-Instruct, a 480B-parameter Mixture-of-Experts model with 35B active parameters. It supports 256K native context length and up to 1M tokens via extrapolation. The model claims state-of-the-art results among open-weight models on agentic coding, browser-use, and tool-use benchmarks, with performance described as comparable to Claude Sonnet 4.
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
Google DeepMind has released Gemma 3 270M, a 270-million parameter compact language model added to the Gemma 3 family. The model is positioned as a highly specialized, hyper-efficient tool for resource-constrained deployments. This extends the Gemma 3 lineup into the sub-billion parameter range, targeting edge and on-device use cases.
Z.ai releases GLM-5.2, a 753B MoE open-weights model claiming top open-model ranking on agentic coding benchmarks
Z.ai released GLM-5.2, a 753-billion-parameter mixture-of-experts open-weights model optimized for long-running agentic coding tasks, with a 1-million-token input context and MIT license. The model ranks first among open-weights models on Artificial Analysis's Intelligence Index v4.1 (score 51, behind Claude Opus 4.8 at 56 and GPT-5.5 at 55) and leads all models on PostTrainBench, a benchmark for agentic fine-tuning tasks. Key technical contributions include a modified sparse attention indexer applied every four layers (cutting per-token computation 2.9x at 1M context), a switch from GRPO to PPO for long-horizon RL training, and a reward-hacking mitigation pipeline using rule-based filters and a judge model. API pricing is substantially below comparable proprietary models, and the release coincides with U.S. government restrictions on access to Anthropic's frontier models.
Sub-billion parameter SLMs outperform zero-shot GPT-5.4 and Claude Sonnet 4.6 on relation extraction benchmarks
A new arXiv paper demonstrates that small language models (360M–3B parameters) fine-tuned on task-specific data can substantially outperform zero-shot frontier LLMs on relation extraction tasks. The best sub-billion model, Qwen2.5-0.5B fine-tuned on pooled general-domain data, achieves micro-F1 of 0.83 versus 0.69 for GPT-5.4 and 0.66 for Claude Sonnet 4.6 in zero-shot settings. The authors attribute the gains to task adaptation rather than model architecture, with a discriminative RoBERTa baseline also exceeding frontier models, and show that 4-bit quantized models deployable on consumer GPUs can match or beat proprietary API-based systems for this narrow task. The work provides evidence that for well-defined NLP tasks with available training data, compact adapted models offer a practical, private, and hardware-efficient alternative to frontier APIs.