AI Agent Papers2026
Prunes tool-output lines inside a coding LLM agent by turning the agent's own internal representations into per-line keep-or-prune labels. Implements a small classification head plus a length-aware embedding, saving up to 39% of tokens across benchmarks while preserving task quality.
Studies train-time knowledge injection via hypernetworks that generate fixed LoRA adapters from large fact corpora, empirically characterizing power-law scaling across hypernetwork depth, width, and target model size and reporting improved OOD generalization.
AI Dataset2026
A multiple-choice benchmark for evaluating language-model arithmetic: 1,000 continuation-style elementary word problems (4 choices, balanced labels) organized by topic, grade band, and difficulty. Designed for base-model continuation log-likelihood scoring; released under Apache-2.0.
AI Dataset2026
A compact evaluation dataset and harness for testing agentic AI on safety-critical robotics tasks. Includes multimodal episodes in parquet format, task-specific eval scripts (gauge reading, human safety monitoring, VLA estimators), and TFDS/Hugging Face integration for reproducible safety evaluations.
AI Model2026
An open-weight LLM checkpoint post-trained for agentic deep search: Qwen-compatible reasoning and tool-call formats optimized for web browsing, multi-source evidence aggregation, long-horizon planning and recovery from failed interactions; typically paired with the AxisAgentic harness.
AI Dataset2026
Provides 7,000 bilingual multi-turn, search-oriented tool-use trajectories (5,000 English, 2,000 Chinese) for supervised fine-tuning and analysis of agentic search models. Includes serialized system/user/assistant messages, embedded Qwen3 tool schemas, and conversion scripts; not a standalone benchmark.
Evaluates spatial cognition of image-generation models by eliciting protocol-constrained visual answers and parsing pixel outputs into structured predictions compatible with existing metrics. Introduces the ProVisE framework and SpatialGen-Bench (470 samples) to compare image-generation models and text-output VLMs on unified spatial tasks.
AI Model2026
A text-only open-weight MOE code model (35B total, 3B active) fine-tuned with SFT+RL for agentic coding; achieves strong agentic-code benchmarks, supports 262k context and deployment via Transformers/vLLM; vision weights are not included.
AI Dataset2026
Evaluates atomic visual perception of multimodal LLMs using 3,000 short visual questions that isolate ten perceptual skills. Built from an error taxonomy across 42 benchmarks, capability-balanced and accompanied by a model leaderboard.
AI Agent Papers2026
Drives long‑horizon desktop agents by reading and manipulating program state (files, DOM, backends) instead of relying on screenshots. The main agent uses code for actions and structural verification while a lightweight GUI subagent handles rare screenshot-click steps, improving success rates and lowering per-task cost versus screenshot-only approaches.
Reranks multilingual retrieval candidates to favour documents that are both semantically relevant and written in the same language as the query, using English-anchored relevance distillation and preference alignment; excels in language-coherence tests while remaining competitive on standard multilingual reranking benchmarks.
AI Model2026
Delivers image and video understanding plus a built-in event‑gated streaming gate — a unified 4B multimodal foundation model that uses codec-aligned tokenization to cut visual tokens by >75% and yield up to 3.5× wall‑clock inference speedup for streaming and long‑horizon video tasks.