AI Coding Live News

On Oct 20, NVIDIA's GEAR lab (Jim Fan's team) open-sourced Flora, a model suite that turns human and robot manipulation video into timestamped action captions, process rewards, outcome rewards and rubric scores. It includes Flora-Captioner 27B and Flora-Rewarder 27B (both on Qwen3.5-27B) and Flora-TempSeg 9B (a LoRA on Qwen3.5-9B), with weights on Hugging Face under an NVIDIA non-commercial license. NVIDIA says it is the in-house data engine used to train GR00T, labeling 200,000 hours of video a day on 512 GB300s, matching GPT-6 Astra on annotation quality at roughly 125x lower cost.

Zoom

Tackling step-level verification in mathematical reasoning and in-context copying bottlenecks in Transformers, NYU/UCLA/Stanford researchers introduce LeanPRM (arXiv:2610.17697)—using the Lean 4 theorem prover to automatically label 152K steps across 10,634 natural-language proofs with zero human annotation, boosting Qwen3-4B step accuracy on LeanPRM-Bench from 48.2% to 74.7% (vs. 60.3% for PRM800K). Meanwhile, Cornell University's Copy-Paste Language Models (CPLMs, arXiv:2610.19247) add a lightweight Copy-Paste head (~3% compute overhead) that relieves the LM head gradient bottleneck, boosting LAMBADA accuracy by +2.5-4.0 points and allowing a w=128 sliding-window CPLM to match full-attention perplexity.

Zoom

Vision-language navigation requires abundant, high-quality language supervision, yet traditional synthetic pipelines generate supervision from static models that lag behind evolving navigation policies. Shanghai AI Lab, Tsinghua, and SJTU introduce RSI-Nav, an embodied recursive self-improvement framework combining instruction-following and instruction-generation in a single model. Using shard-wise dual bootstrapping on unlabeled trajectories, RSI-Nav achieves state-of-the-art 68.6% SR on R2R-CE and 72.4% SR on RxR-CE without human intervention.

Zoom

While deep research (DR) agents excel on synthetic and academic queries, their reliability in realistic personal life and professional workflows remains uncharted. Tencent Hunyuan introduces LifeSearch, a rigorous benchmark featuring 203 real-user tasks across 7 domains backed by 4,500+ hours of expert annotation and 4,000+ fine-grained rubrics. Evaluating 12 leading DR agents reveals that the strongest frontier agent scores only 63.4%, unmasking persistent bottlenecks in multi-step information synthesis and constraint verification.

Zoom

On 2026-10-12 @OpenAIDevs highlighted ChatGPT desktop browser Annotations extensibility (document.oai.annotation): sites can customize selection targets, metadata and preview controls, and pair them with WebMCP site tools so agents receive the user's selected page context and can act through the site's own capabilities. Docs target DevDay 2026+ desktop; Enterprise/Edu need admin policy.

Zoom

Computer-Use Agents (CUAs) designed to operate graphical desktop environments through virtual keyboard and mouse interactions are traditionally evaluated using outcome-based functional verifiers that assess only the final state after hundreds of operational turns. This black-box approach obscures whether failures stem from syntax typographical errors, GUI bounding-box misalignments, or intermediate state drift, preventing actionable diagnostic insights. NVIDIA Research introduces OSWorld-Pro (arXiv:2609.24890), the first comprehensive process-based evaluation suite for computer-use agents. Spanning 300+ complex desktop workflows decomposed into 2,800+ sequentially dependent subgoals grounded in 67,000+ expert human annotations, OSWorld-Pro deploys calibrated LLM judges to track incremental subgoal completion. Evaluations reveal that OSWorld-Pro presents a formidable challenge to state-of-the-art models: frontier models like Claude Opus 5 achieve only 75.7% (compared to 83.4% on standard OSWorld), systematically isolating critical procedural failure patterns such as exploratory irrelevant actions and click grounding drifts.

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

Comet Opik 2.2.84 (2026-09-29) lets online LLM-as-a-Judge rules call TypeSafe Jev end-to-end via OpenRouter POST /api/alpha/decisions (not chat/completions). Each Boolean metric becomes a yes/no question answered in one call; score 1 if probability ≥0.5, with Probability: 0.93 in the reason. Backend adds OpenRouterDecisionsClient (workspace OpenRouter key, 429/5xx retries) for ~typesafe/jev-latest / typesafe/jev-1.13. Also: Annotation Queue automation + item provenance. ~8 commits / 104 files vs 2.2.83.

Zoom

Amazon's AI Research division has open-sourced 'Rufus-Air: An Open LLM Post-Training Recipe' (arXiv: 2609.29421), an entirely reproducible eight-stage post-training pipeline built atop GLM-4.5-Air-Base (a 106B total / 12B active parameter Mixture-of-Experts model). Dispensing with proprietary teacher distillation and private human annotation, Rufus-Air cascades through eight distinct stages—SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF—leveraging solely public data and open tooling to beat the official GLM-4.5-Air checkpoint across standard benchmarks.

Zoom

Comet Opik 2.2.81 (2026-09-25) routes scored entities into annotation queues, optionally provisions an extended free-form SQL ClickHouse user, registers 19 canonical providers so model prices load, and fixes Gemini usage, streamed Mistral reasoning, and slots=True dataclass encoding in the SDK.

Zoom