AI Coding Live News

On Oct 26 Tencent Hunyuan (Tencent Hy) open-sourced Hy-SimulMT, a real-time simultaneous interpreting model for bidirectional Chinese-English speech-to-speech translation. It translates while the speaker talks, outputs both translated text and speech, and can clone the speaker's voice in real time. Six checkpoints landed on Hugging Face (30B-A3B translation-only and source-plus-translation Interleave variants, each in BF16, FP8 and GGUF), with the model card listing Apache-2.0; GitHub ships the SimulInfer serving stack and SimulTrain training tools. Vendor-reported: about 3s StreamLAAL on RealSI long-form audio, the lowest among compared systems.

Zoom

Tencent ARC in collaboration with Tsinghua University released and open-sourced Looking Ahead (arXiv:2610.29989, GitHub: TencentARC/Looking-Ahead), establishing a breakthrough paradigm for autoregressive video synthesis. Overcoming the chronic pathology of traditional autoregressive video models—where unidirectional sequential extrapolation causes exponential error accumulation and severe visual collapse over extended rollouts—Looking Ahead introduces Lookahead Attention. By coupling casual autoregressive decoding with a forward-looking planning stream that anchors future spatiotemporal keypoints, the framework eliminates cumulative drift and visual jitter in long-form generation.

Zoom

Modern 3D world models typically use view-dependent features from geometry foundation models (GFMs) as predictive states, entangling camera-induced variations with physical scene dynamics. Tongji University and Tencent introduced GeoState (arXiv:2610.22343). By aggregating multi-view GFM features into a view-decoupled 3D scene state, GeoState models physical scene evolution independently of camera viewpoints, maintaining a single context-derived scale throughout rollouts without per-frame scale realignment.

Zoom

Deep search agents struggle with credit assignment across long, noisy retrieved contexts. Zhejiang University and Tencent open-sourced KnowGPO (arXiv:2610.22331, GitHub: ZJU-REAL/KnowGPO), an RL framework that groups search trajectories by atomic knowledge conditions rather than surface observations. Qwen3-8B fine-tuned with KnowGPO achieves 38.8% on BrowseComp-ZH and 40.2% on GAIA, outperforming GRPO/GiGPO baselines and rivaling 32B open-source search systems.

Zoom

On Oct 16 Tencent Hunyuan open-sourced Hy Memory 2.0 in three layers: the Apache-2.0 memory-writer model Hy-Memory-30B-A3B (~3B active, HF weights plus arXiv report), a Python SDK covering Chat, Working and Coding scenes (PyPI hy-memory 2.0.x), and local-first MemHub (CLI + macOS, preview). Per Tencent, swapping it in as the writer across Mem0, MemOS, Hy-Memory and held-out EverMemOS yields a 55.49 average vs 54.62 for Claude Opus 5, measured on fixed 20% subsamples; it still trails Opus 5 on several individual metrics.

Zoom

Terminal agents frequently struggle to convert partial command-line progress into complete end-to-end task resolution. Researchers from Tencent AI Lab and NUS introduce Terminal-RSI, alternating Recursive Self-Rewrite (RSR) of verified trajectories with critic-inheriting Recursive Policy-Refine (RPR) alongside Turn-Boundary Skip-Observation GAE (TB-GAE). Evolving Qwen3.8-27B across five stages yields Terminal-RSI-27B, achieving 86.52% on Terminal-Bench 2.1 and 79.00% on Terminal-Bench Hard.

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

To improve credit assignment in long-horizon agentic tasks, combining reinforcement learning with verifiable rewards (RLVR) and on-policy self-distillation (OPSD) has emerged as a leading paradigm. However, existing pipelines neglect the dynamic evolution of agentic skills and the reliability of privileged teacher signals. Researchers from CUHK and Tencent introduced RSIPO, enabling skills and policies to co-evolve recursively. RSIPO extracts skills directly from trajectory rollouts, optimizes skill generation via replay, and employs Empirical Bayes shrinkage to calibrate student trust in teacher logits. Operating on Qwen2.5-7B, RSIPO achieves 98.6% success on ALFWorld, outperforming standard GRPO by 17.4 percentage points.

Zoom

Terminal coding agents are expanding from standard software engineering into scientific domains like bioinformatics, materials science, and physics. However, building training sandboxes requires executable reference behavior and rigorous verifiers capable of distinguishing true semantic correctness from superficial syntactic mimicry—a process that currently requires tedious manual engineering per task. Researchers from Tsinghua University and Tencent introduce Software-in-the-Loop Reconstruction (SWR, arXiv:2610.02710), a self-supervised environment scaling framework. SWR extracts ground-truth outputs and verifiers from existing executable scientific software workflows by perturbing input configurations into public observations and hidden evaluations. Agents synthesize complete, editable programs from input-output schemas without viewing source code, evaluated by hierarchical verifiers testing semantic fidelity, structural integrity, and anti-shortcut compliance. Implemented across 500 workflows and 46 software suites spanning six scientific domains, SWR generates 1,422 verified trajectories. Supervised fine-tuning of Qwen3.8-27B elevates Terminal-Bench 2 average success from 47.94% to 53.56%, establishing a scalable paradigm for scientific terminal agent training.

Zoom

Collecting successful trajectories for complex terminal tasks is essential for post-training coding agents. However, solving difficult tasks often relies on specialized harnesses that incorporate domain assumptions unavailable during real-world deployment; naive SFT on these traces causes verifier leakage and harness over-fitting. Researchers from the University of Maryland and Tencent AI Lab introduce Recursive Self-Rewrite (RSR, arXiv:2610.02826). Using a single foundation model (Qwen-3.8-27B), RSR pairs a planner (extracting operational runbooks), a critic (eliminating leakage), and an executor (replaying runbooks in fresh isolated sandboxes). RSR expands 2,001 specialized source rollouts into 11,094 clean general-harness trajectories, boosting Terminal-Bench 2 Pass@3 from 57.0% to 74.2% and surging Terminal-Bench Hard success from 39.0% to 63.0%.

Zoom

On-policy self-distillation (OPSD) trains mathematical reasoning models by deploying a privileged teacher that observes ground-truth solutions to supervise student-sampled prefixes. Standard OPSD fixes the teacher parameters across all states, leaving valuable supervision untapped. Researchers from Tencent WeChat and Tencent AI Lab propose Neighborhood OPSD (N-OPSD). They discover that local parameter perturbations in the privileged teacher reveal complementary, reference-aligned corrections across distinct token positions. Offline greedy pruning compiles a compact pool of frozen neighbor experts, while an online MaxPeak and quantile router dynamically selects the optimal expert distribution. Across AIME 2024, AIME 2025, and HMMT 2025, N-OPSD improves Average@12 by up to 2.75 points on Qwen3-1.7B, 4B, and 8B models without any inference overhead.

Zoom

High-throughput LLM inference engine SGLang released milestone v0.5.20, consolidating 713 merged PRs from 237 contributors. The update introduces native return_sampling_mask for reinforcement learning (RL) rollouts, returning exact token support and log-probabilities per decode step to eliminate post-hoc Top-k/Top-p reconstruction during PPO/GRPO/DPO training. Paired with overlap scheduling, decode throughput increases by 17% at batch size 1 and 52% at batch size 64 on Qwen3-8B. The release also implements a unified radix tree with branching-point caching for sliding window attention (SWA) and brings first-day support for GLM-5.3-Flash, Tencent Hy4-Preview, and Qwen3.8-Flash-Next.

Zoom

Tencent Hunyuan in collaboration with Fudan University's NLP group has open-sourced ExplorationBench (arXiv: 2609.30199, Project: explorationbench.com), establishing a rigorous framework to quantify an AI agent's genuine scientific exploration and hypothesis-testing capacity. To prevent models from cheating via pre-training memorization, the benchmark introduces 'Alien Worlds'—computational sandbox environments (AlienCode and AlienLogic) governed by strictly executable rules that directly contradict terrestrial intuition. Agents must actively frame hypotheses, design probe experiments via API tools, and revise causal models under feedback.

Zoom

Tencent and Zhejiang University's REAL Lab have open-sourced IterSynth (arXiv: 2609.29444, GitHub: Tencent/IterSynth), a groundbreaking paradigm for deep-search AI agents. Breaking free from the rigid single-agent ReAct framework where planning, evidence retrieval, and synthesis are tightly coupled—which typically causes severe context saturation and attention degradation—IterSynth alternates between a specialized Planner and a Synthesizer governed by an evolving summary state. Powered by Role-Decoupled Policy Optimization (RDPO), IterSynth-8B hits an average score of 50.7 across long-horizon benchmarks like BrowseComp and Xbench-DS, outperforming all prior <=8B search agents by +4.2%.

Zoom