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.
AI Agent Papers2026
Generates large-scale, explorable 3D open-world scenes from open-ended text prompts, producing editable instance-level assets and a consistent global terrain. Uses agentic planning to convert text into region/terrain/asset specifications and a coarse-to-fine pipeline for terrain construction, mesh reconstruction, and render-based refinement.
AI Agent Papers2026
Orchestrates reasoning, external tool use, and native image generation under one unified multimodal agent policy via post-training. Introduces RAD-GRPO for agentic reinforcement fine-tuning and releases training data plus the full post-training infrastructure.
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 Agent Papers2026
Converts sparse trajectory-level rewards into turn-level credit by aggregating token-level teacher–student log-probability gaps and recursively updating a Bayesian belief in log-odds; produces turn-wise reweighting for policy optimization without an extra critic or rollouts.
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.
AI Model2026
A 29.6B-parameter multimodal causal language model with a dedicated ViT-G/14 perception encoder for running agentic, tool-using, multimodal reasoning locally on consumer hardware. Offers 4-bit quantized weights and a DFlash drafter for speculative decoding to reduce memory and speed up generation.
AI Model2026
A GGUF release of Meta's Muse Glimmer 30B optimized for local multimodal agent inference; includes two quantized text builds, a perception encoder for image input, and an optional DFlash drafter for speculative decoding—fits on 24–32 GB VRAM.
AI Model2026
Runs a quantized, locally executable 29.6B multimodal causal language model optimized for agentic workflows. Includes a perception encoder for image+text input, 4-bit quantized weights for 24–32GB devices, a DFlash drafter for speculative decoding, and robust tool-call support.
A research report proposing a continual-learning agent workflow that pairs recursive self-improvement with a Mixture-of-LoRA design: freeze a foundation model, compose specialist LoRA adapters routed per user turn, and support them with long-context RL and post-training infrastructure.