AI Coding Live News

Krafton AI, the research division of global gaming giant Krafton, officially announced the open-weights release of Raon-1 mini under Apache 2.0. Pretrained from scratch, Raon-1 mini features a sparse Mixture-of-Experts (MoE) architecture with 30 billion total parameters and only 4 billion active parameters per token. The release is accompanied by a dedicated DFlash speculative drafting model and a live interactive playground. Internal evaluations reveal that Raon-1 mini matches Meta's Muse Glimmer across agentic tool-use and coding benchmarks while requiring substantially lower VRAM and sustaining lower generation latency.

Zoom

While supervised fine-tuning (SFT) distills agentic tool-use capabilities from frontier LLMs into small language models (SLMs, 0.6B to 8B parameters), student agents frequently suffer from 'progress stagnation'—collapsing into repetitive, unproductive tool-calling loops as interaction trajectories extend. In arXiv:2610.19439, researchers introduced Progress-Aware Distillation (ProD). ProD defines a rigorous stagnation scoring formulation that dynamically identifies and penalizes stagnant behavior during student trajectory rollouts via an adaptive SimPO-inspired margin. Experiments across 8 diverse SLMs prove ProD effectively eradicates repetitive loops while boosting task completion efficiency and success rates.

Zoom

To combat goal drift in long-horizon agent tool-use and multi-agent systems, NUS, USTC, and Alibaba Qwen introduced Steering Agent (arXiv:2610.22316). Jointly trained via pairwise ranking and Group-Relative Policy Optimization (GRPO), the agent operates a low-cost fast path to detect drift and a slow path to generate grounded interventions. It raises Multi-Hop QA benchmark performance from 42.70 to 50.10 while cutting executor turns from 8.8 to 6.5 (-26.1%) without modifying the underlying executor models.

Zoom

On Oct 13 Liquid AI released LFM2.5-24B-A2B, the largest and final LFM2.5 model: 24B total parameters, ~2.45B active per token, 131K context, and always-on reasoning. By Liquid's own numbers it leads or matches Qwen3.6-35B-A3B on 5 of 8 tool-use/agent benchmarks (AutomationBench 27.69 vs 8.72) while trailing on SWE-Bench Verified, GPQA and other knowledge/coding tests. Open weights are on Hugging Face with GGUF, MLX, FP8 and ONNX builds; API pricing is $0.10 / $1.00 per million tokens and it is also on OpenRouter.

Zoom

Recent attempts to scale tool-use post-training for autonomous agents have focused primarily on synthesizing standalone execution environments. However, environments constitute merely one component of a holistic agentic interaction system comprising environments, tasks, harnesses, and evaluators; scaling environments in isolation yields inconsistent training signals. Researchers from Fudan University introduce WEFT (arXiv:2609.36887), a whole-system evolution framework for tool-use post-training. WEFT coordinates environment breadth, task complexity, and interaction diversity, applying execution-driven self-evolution to attribute failures and iteratively revise flawed components. To ensure optimization stability and concurrency reliability, WEFT introduces prefix-preserving sampling, atomic-turn credit assignment, and MegaMCP—a Model Context Protocol infrastructure providing isolated, recoverable state management across concurrent rollouts. WEFT-8B and WEFT-14B outperform matched environment-scaling baselines across BFCL V4, tau^2-Bench, and Claw-Eval, with WEFT-14B beating Agent-World-14B by 6.41, 2.23, and 12.27 percentage points, while WEFT-35B-A3B excels on long-horizon benchmarks like Toolathlon-Verified.

Zoom

Real-world embodied tasks require agents to operate physical tools under geometric constraints while tracking object state transitions. Despite strong perception benchmarks, current multimodal video LLMs struggle with tool-centric physical reasoning. NTU S-Lab and collaborators introduce EgoTools, the first comprehensive suite for egocentric tool-use reasoning. It features EgoTools-Data (100 hours of synchronized egocentric tool videos with 3D annotations, audio, and dense causal narrations) and EgoTools-Bench (1,000 QA pairs across perception, geometry, procedural progress, and causal inference). Probing reveals frontier models struggle with physical grounding (Gemini-3.1-Pro scores only 51.7% on grounding), while supervised fine-tuning on EgoTools-Data lifts Qwen3-VL-8B-Instruct accuracy from 50.0% to 60.9%.

Zoom

BerriAI shipped LiteLLM v1.103.2 on 2026-10-01 (PyPI ~06:20Z; 17 commits vs 1.103.1): forward Claude Code safeguards / dangerous-tool-use beta unchanged to Anthropic, Bedrock, Vertex, and Azure AI Foundry so auto mode works behind the proxy; attribute CLI session spend to a per-user cli-session alias for daily activity BI; restore pre-config-wins for pass-through endpoints.

Zoom

Meta released Muse Glimmer in August, a 30B open-weight local agent model under Apache 2.0 whose quantized weights fit under 20 GB for consumer Macs and single-GPU PCs. On October 19 Meta published its technical report: a ~29.6B dense design distilled from Muse Spark that, by Meta's figures, beats Gemma4-31B and Qwen3.6-27B on tool-use and agent benchmarks such as MCPAtlas, tau3-Banking and SWE-Bench Pro, while still trailing Qwen3.6-27B on SWE-Bench Verified, TerminalBench 2.1 and OSWorld.

Zoom