Discover the Best AI Resources

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Provides a terminal-style benchmark of 46 long-horizon tasks decomposed into fine-grained graded subtasks to produce dense intermediate rewards and partial credit, enabling evaluation of long-horizon planning, long-context management, and iterative debugging. Tasks typically require hundreds of episodes and minutes-to-hours of execution; baseline evaluations report high token and episode consumption with low pass rates, highlighting evaluation headroom.

Blood Pathology LIMS Environment

Simulates a hospital LIMS to benchmark agentic clinical reasoning: agents inspect demographics, medications, lab orders/results and then submit ICD‑10 diagnostic reports scored by deterministic, context‑aware graders. Ships as an OpenEnv/FastAPI runtime with 8 scenarios, step‑level rewards and trajectory capture for RL, tool‑use and evaluation.

Digital Hospital Environment

Evaluates agents inside a structured hospital workflow via a downloadable FastAPI runtime that enforces role-specific tool permissions, evidence-before-treatment discipline, deterministic grading, dense process rewards, and full trajectory logging. Designed for RL, offline policy learning, multi-agent workflow research and process-supervision datasets; not for real patient care.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

Evaluates proactive, multimodal agents on 400 bilingual real‑world tasks across five capability axes (Skill Usage, Exploration, Long‑Context Reasoning, Multimodal Understanding, Cross‑Platform Coordination) using live Docker‑based, stepwise closed‑loop evaluation to separate base model skills from framework design.

Qwythos-9B-v2-GGUF

Provides GGUF-quantized builds of the Qwythos-9B-v2 LLM for local runtimes, with multiple quant levels, optional MTP-enabled variants, a 1,048,576-token context window, and an optional BF16 vision projector for multimodal use.

Qwythos-9B-v2

A 9B-parameter Qwen3.5-based multimodal model tuned to preserve chain-of-thought reasoning while eliminating repetition loops; restores native multi-token prediction, supports 1,048,576-token context, and targets research/red-team use.

Video Generation Models are General-Purpose Vision Learners

Uses large-scale text-to-video generative pretraining to create GenCeption, a feed-forward perception model that performs diverse vision tasks from text instructions—depth, surface normals, camera pose, referring segmentation, and 3D keypoints—often matching or surpassing specialized models while requiring far less task-specific data.

Scalable Visual Pretraining for Language Intelligence

Explores unsupervised visual pretraining on visually rich documents to improve language-model intelligence; shows visual-pretrained models outperform text-only counterparts on the same corpora. Key aspects: direct use of images/layouts (no OCR-only pipeline), scalable across backbones and benchmarks.

4D Human-Scene Reconstruction from Low-Overlap Captures

Reconstructs 4D dynamic human scenes from sparse, low-overlap multi-camera captures by decoupling background synthesis and human modeling. Synthesizes hundreds of camera-controlled background views with a video diffusion model, initializes deformable Gaussian humans via cross-view identity and triangulated keypoints, then applies motion-adaptive recursive enhancement to reduce artifacts.

jakubkrehel/skills

Gives coding agents practical guidance for designing and reviewing interfaces, covering accessibility, layout, writing, typography, color and UI polish. Skills can be used through the Skills CLI or as a Claude Code plugin.

Wan-Dancer-14B

Generates minute-scale, temporally coherent dance videos from full music tracks using a hierarchical two-stage approach: global keyframe planning plus local temporal refinement; suitable when long-range musical structure and rhythmic continuity matter.

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Proposes Riemannian Isometric Policy Optimization (RIPO) to fix exploration collapse in PPO-style RL for LLMs by aligning policy updates with the policy manifold's Riemannian geometry, improving exploration–exploitation balance and optimization stability across competition benchmarks.