AI Agent Papers2026
Reformulates long-horizon agent execution as explicit task-state management: a manager defines bounded subtasks, fresh-context executors run them, and read-only auditors verify outcomes. Shows large performance gains on WeaveBench, Terminal-Bench and OSWorld.
Supervises audio reasoning by generating per-sample, audio-grounded rubrics that evolve with model rollouts and serve as reinforcement-learning rewards, improving perception and adaptive multi-step reasoning while avoiding reward saturation.
AI Model2026
A 20B ternary-weight Mixture-of-Experts reasoning LLM optimized for on-device and low-memory inference—delivers high throughput (200+ tok/s on M4) and an extremely long 131k-context for math/logic benchmarks, but is a preview with limited agentic fine-tuning.
AI Agent Papers2026
Turns open-ended everyday requests into a managed long-horizon execution process that decomposes tasks into bounded subtasks, maintains compact execution memory under context pressure, and verifies and repairs final deliverables. Designed to run unchanged across multiple LLM backends and evaluated on AgentIF-OneDay.
Evaluates how large language models fabricate user attributes in personalization and whether model self-monitoring is a reliable signal. Introduces MirageBench (150 personas, 6 personalization tasks, judge-validated faithfulness taxonomy) and a 12-model leaderboard revealing pervasive over-inference and a 'Self-Monitoring Inversion'.
AI Model2026
A 27B-parameter causal language model with a native vision encoder for image/video+text understanding, long-horizon agentic tasks, and tunable thinking-mode reasoning. Native 262,144-token context (extensible to 1,000,000) and production-focused inference recipes.
AI Video Papers2026
Evaluates VLMs' ability to form global spatial awareness from long-horizon egocentric video. Introduces GST-Bench: a VQA benchmark with human-verified questions from 6,790 minutes of synthetic video, reveals a large gap (best zero-shot 42.68 vs human 79.08) and provides GST-Train dataset.
Replaces external environment interaction in agentic RL training with 'world rehearsal': the policy alternates between making tool calls and simulating their environment responses, jointly optimizing both roles so the agent internalizes environment dynamics and improves long-horizon tool use and transfer.
AI Dataset2026
Evaluates schema-guided structured extraction from documents: given a document and a JSON schema, systems must return a schema-valid JSON with page-and-box grounding. Covers 370 documents (4,869 pages) across 8 business domains and 67 document types; scores value accuracy, word/page grounding, and long-list completeness.
AI Agent Papers2026
Transfers hierarchical, structured memory from a large teacher agent into small LLM agents to improve tool-use success. Constructs Workflow, Subtask and Function memories with proactive/reactive injection; training-free and validated on multiple tool-use benchmarks.
AI Agent Papers2026
Enables a coding agent to self-develop by evolving its harness, prompts, tools, and core code via reviewed commits — supporting recursive free evolution and experience-driven evolution. Demonstrated a 161-day live lineage and state-of-the-art scores on multiple coding benchmarks while foregrounding operational safety.
Yingpeng Ma, Jianhao Yan +7Affiliation: NLP2CT Lab, University of Macau, Macau, China, Affiliation: Westlake University, Hangzhou, China +3
Evaluates whether LLM-driven storyteller agents preserve long-horizon logical consistency under adversarial player interventions. Introduces NCP-Bench (100 movie-derived narrative environments) with structured trajectory/commitments and automatic violation checks; finds strong LLMs often contradict themselves across multi-turn interactions.