AI Agent Papers2026
Turns raw datasets into verifiable multimodal news features via a multi-agent newsroom pipeline. Key innovations: (1) an Inspector that links each claim to data/code/external references for re-execution and audit; (2) multimodal asset generation (interactive maps, audio, visuals) tailored to the story.
Shifts branching and credit assignment in agentic RL from coarse units to fine-grained decision points in generated sequences. Uses a Branching Score combining token uncertainty and policy-induced likelihood gains plus procedure-level advantage scaling; improves performance across 13 benchmarks while keeping efficient tool calls.
AI Agent Papers2026
Orchestrates teams of sub-agents across text, image, audio and video by modality-aware task decomposition, online sub-agent specialization, and parallel execution; introduces DA-GRPO to train Orchestra-o1-8B and reports a ~10.3% accuracy improvement on the OmniGAIA benchmark.
AI Video Papers2026
Proposes chunk-level multimodal retrieval and chunk-adaptive reranking for retrieval-augmented generation on long egocentric videos; introduces V-RAGBench to decouple retrieval vs. generation evaluation and CARVE to run parallel retrievers and select per-chunk configurations.
AI Dataset2026
Benchmark for evaluating multimodal LLM safety in Korean cultural contexts — includes KSAFE-MM-G which localizes global safety queries into Korean scenarios and KSAFE-MM-C which targets culture-specific visual-textual vulnerabilities. Provides curated image–text pairs and jailbreak-style prompts to reveal both unsafe behaviors and over-refusal.
AI Dataset2026
Provides kanji-level evaluation data for Japanese TTS: disambiguated sentence contexts targeting 4,378 kanji-reading pairs (2,136 Jōyō kanji) with 13,095 native-speaker–verified sentences and katakana-marked ground-truth readings for kanji-level error metrics.
AI Model2026
A 3B-parameter causal LLM tuned for verifiable multi-step reasoning in math, coding and STEM using a Spectrum-to-Signal post-training pipeline (SFT, RL, offline self-distillation); not recommended for tool-calling/agent tasks.
Frames AI research as a trainable practice of reading, building, debugging, and fast feedback. The essay is most useful for researchers learning how to avoid hype-chasing, benchmark tunnel vision, and agent-induced blind spots.
Uses Parallel Looped Transformers (PLT) to make loop count a practical knob for code models, finding two loops give the best test-time gains. Trains 7B models on 18T tokens and attributes saturation beyond two loops to a gain–cost tradeoff from positional mismatch.
AI Agent Papers2026
Assesses whether coding agents can generate complete, playable games end-to-end inside the Godot engine. Implements an interaction-grounded evaluation (replayed demonstrations + rubric-guided multimodal judging) across 140 tasks and 15 game families; top agents score ~41%.
Proposes ZPPO, a distillation method that keeps the teacher inside prompts rather than injecting teacher gradients, using binary- and negative-candidate prompts plus a prompt replay buffer to recover learning signal on hard examples; shows gains for small Qwen3.5 students across 31 multimodal benchmarks.
Evaluates multimodal LLMs' ability to reconstruct past observations and act in controllable non-Markov games. Introduces RNG-Bench with two games (Matching Pairs, 3D Maze), three controllable difficulty axes, a head-to-head duel protocol, and a Memory Gap metric to separate forgetting from action errors.