AI Coding Live News

Autonomous research agents hold the promise of sustaining AI self-improvement by iteratively proposing hypotheses, tuning models, and refining post-training pipelines. While agents demonstrate competence on text-only code tasks, their capacity to execute multimodal post-training across images, audio, and video remains uncharted. Researchers introduce MMPostTrainBench (arXiv:2610.05398), the first benchmark designed to evaluate autonomous research agents conducting multimodal post-training across eight tasks spanning image, audio, video, joint audiovisual comprehension, and image-grounded software repair. Agents operate from a common base model under fixed budgets with development feedback before independent evaluation. The audit reveals sobering realities: across all tasks, 52.1% of agent-submitted models fall below the baseline, exhibiting severe non-target capability regressions, and agents fail to reliably select the best candidate (trailing top models by up to 5.38 percentage points). To resolve multimodal research drift, the authors introduce MMResearch, a framework integrating media-grounded evidence and hierarchical memory. Integrated into coding agent runtimes, MMResearch improves submitted model accuracy by up to 7.75 percentage points for Claude Code (Claude Opus 4.8) and 2.33 points for Codex (GPT-5.6).

Autonomous deep research agents are expanding beyond text-centric search toward multimodal discovery across high-resolution imagery, complex charts, and long-horizon video. However, existing multimodal models struggle to ground fine-grained visual anchors and bridge perceptual evidence with external search verification. Researchers from Fudan University and collaborating institutions introduce OneSearch-VL (arXiv:2610.12419), a unified multimodal deep research agent for single-image, multi-image, and video environments. OneSearch-VL centers on the Visually Grounded Evidence Graph (VGEG), which explicitly encodes localized visual anchors, entity relationships, source-supported facts, and research operations into a shared dependency topology. Leveraging VGEG, the authors construct OneSearch-VL-SFT-110K and OneSearch-VL-RL-10K datasets alongside an Evidence-aware Visual-Grounded Rubric reward (EVGR) to supervise visual traceability during reinforcement learning. On the newly introduced OneSearch-MI-Bench and OneSearch-Video-Bench, OneSearch-VL-8B outperforms tool-augmented Qwen3-VL-8B by 20.2 and 17.6 percentage points respectively, while setting new state-of-the-art results across seven established image benchmarks and VideoDR, with code fully open-sourced.

Autonomous deep research agents (such as OpenAI Deep Research and Perplexity) represent a powerful leap toward automated knowledge synthesis. However, on open-ended and comprehensive inquiries, existing agents rely primarily on unconstrained search-and-generate loops. This leads to three systemic failures: redundant query loops, conflicting claims across sections, and runaway token expansion. Researchers from Tsinghua University and Renmin University of China unveil IOEDR (arXiv:2610.11566), a framework for Incremental Open-Ended Deep Research with a Structured Harness. IOEDR models the evolving research report as a dynamic hierarchical state graph coupled with a persistent, deduplicated evidence pool. Rather than executing open-ended browsing, the agent uses structured harness constraints to incrementally plan sections, identify specific evidential gaps, and trigger precision queries with dynamic termination conditions. On DeepResearch Bench, IOEDR achieves superior report coherence and verifiable fact density while reducing total token consumption by 33.2% and slashing search API requests by 61.4%.

_akhaliq shared HarnessDev, a paper asking whether LLMs can create and evolve their own agent harness—the runtime scaffolding for tools, loops, and execution—instead of relying only on hand-written agent frameworks. It matters for coding and research agents that need cheaper, self-improving harnesses.

Ant Ling (AntLingAGI) open-sourced Ling-3.0-flash-Fin for real-world finance workflows and FinFIRST, an expert-built benchmark for financial search agents, aiming to make financial AI more accessible and verifiable. SGLang already announced Day-0 serving; this is the primary open-source + benchmark announcement.

_akhaliq shared Repo-To-Skill: DisCo distills operational know-how from GitHub repos into compact, verified skills that ML research agents can load on demand. The AREX-Skill library holds 5,000+ verified skills from 1,000+ repos and reports large MLE-bench gains.

Anthropic released Fellows research showing Claude can research alignment methods, train, and evaluate smaller models on its own given 48 hours and a single GPU. Across 10 measurable failure modes such as deception and sycophancy, Claude improved safety scores without degrading general capabilities, then tested whether the winning recipes transferred. The best methods generalized to held-out benchmarks, the Petri behavioral audit, and models up to 4.7x larger. In a first successor-alignment test, Sonnet 5 post-trained an early Opus 4.8 checkpoint to safety scores approaching production Opus 4.8, which had gone through Anthropic's full alignment stack. The company is releasing the automated alignment research setup for others to build on, while warning that subtle or rare failures may have no benchmark at all, so measurement remains the binding constraint. For labs running coding and research agents, this is early evidence that weaker models can help align stronger successors rather than only generating more capability.