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.
Related guides (4)
Related events (8)
Kimi K2.6: Moonshot AI's 1T-Parameter Vision-Language Model Matches Open-Weights Peers, Trails Top Closed Models
Moonshot AI released Kimi K2.6, a 1 trillion-parameter mixture-of-experts vision-language model with 32B active parameters, designed for long-horizon autonomous coding sessions lasting multiple days and multi-agent orchestration scaling to 300 parallel subagents executing up to 4,000 steps. The model matches Qwen3.6 Max Preview and DeepSeek-V4-Pro on the Artificial Analysis Intelligence Index (scoring 54 vs. their 52) while trailing closed models like GPT-5.5 and Claude Opus 4.7. Weights are freely downloadable from Hugging Face under a modified MIT license permitting commercial use, with API access priced at $0.95/$0.16/$4.00 per million input/cached/output tokens. Notable features include a 256K token context window, native INT4 quantization, a 'preserve thinking' mode for multi-turn reasoning continuity, and a research preview 'claw groups' feature enabling cross-developer agent collaboration.
MobileMoE: Scaling Mixture-of-Experts for Sub-Billion Parameter On-Device Deployment
MobileMoE introduces a family of on-device MoE language models with 0.3–0.9B active parameters and 1.3–5.3B total parameters, targeting mobile deployment under memory and compute constraints. The authors derive an on-device MoE scaling law identifying a sweet spot of moderate sparsity with fine-grained and shared experts, then train models through a four-stage recipe including quantization-aware training on open-source data. Across 14 benchmarks, MobileMoE matches or exceeds leading dense on-device LLMs with 2–4× fewer inference FLOPs, and delivers 1.8–3.8× faster prefill and 2.2–3.4× faster decode than dense baselines on commodity smartphones at comparable INT4 memory.
GLM-5.1 Open-Weights Model Targets Long-Running Agentic Tasks; Andrew Ng on Coding Agent Acceleration by Software Domain
Z.ai released GLM-5.1, an open-weights mixture-of-experts LLM (754B total / 40B active parameters) designed for sustained agentic coding tasks lasting up to eight hours, featuring iterative planning-execution-evaluation loops with thousands of tool calls. The model claims top open-weights performance on Artificial Analysis Intelligence Index and SWE-Bench Pro, available under MIT license via HuggingFace. The accompanying editorial by Andrew Ng offers a tiered framework for how much coding agents accelerate different software work categories—frontend most, then backend, infrastructure, and research least—with practical implications for team organization. A secondary item references data-center opposition and LLM helpfulness failure modes.
AgentBeats: Standardized Agent Evaluation via A2A and MCP Protocols
A new arXiv preprint proposes Agentified Agent Assessment (AAA), a framework where evaluation is performed by judge agents interacting through standardized protocols—A2A for task management and MCP for tool access—rather than bespoke benchmark harnesses. The authors introduce AgentBeats as a concrete implementation, validated through a five-month open competition with 298 judge agents and 467 subject agents across 12 categories, plus a coding-agent case study. The work addresses fragmentation in agent evaluation by decoupling assessment logic from agent implementation, enabling reproducible and interoperable benchmarking.
AARRI-Bench evaluates frontier LLMs and agents on granular research-intern-level tasks
Researchers introduce AARR (Act As a Real Researcher), a new benchmark series targeting whether AI agents can emulate the professionalism, thoroughness, and nuanced judgment of human researchers in granular research scenarios—not just macro-level task execution. The first benchmark, AARRI-Bench, tests frontier models and agentic harnesses, finding that even the best configuration (Mini-SWE-Agent with Claude Opus 4.7) achieves only 68.3% success, frequently missing subtle but critical details obvious to human researchers. The work argues that closing the gap requires deeper modeling of research behavior rather than more complex scaffolding.
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.
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.
Agentopia: Long-term multi-agent life simulation framework for training LLMs on social behavior
Researchers introduce Agentopia, a framework for simulating 10 years of social life across 100 LLM-powered agents, enabling study of emergent social behaviors and long-term personal growth dynamics. The system defines a 'life reward' metric mirroring human well-being and uses it to train LLMs via rejection sampling. Training on simulated social experience yields a +15.6% improvement on downstream role-playing benchmarks, suggesting that synthetic social simulation can generalize to real capability gains.