…An Open-Source Agentic Modeling Framework Published on May 14 Submitted by Qianhui WU on May 15 Microsoft Research Authors: , , , , , Rui Yang , , , , , , , , Abstract Orchard is an open-source framework for scalable agentic…
…Towards Training a Multimodal Agentic Search Model from Scratch (2026) E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning (2026) PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training (2026) $S^3…
…Yanxi Chen , , , , , , Abstract Large language models can be trained through reinforcement learning to develop a meta-capability enabling continuous learning and adaptation across long sequences of tasks in dynamic environments. Generated by…
…Experiments show that WorldCraft enables accurate object control, preserves the video-based world model's camera fidelity under camera-only evaluation, and maintains object state across long autoregressive rollouts with off-camera…
…Rethinking Optimization Granularity in On-Policy Distillation Published on Jun 1 Submitted by Hangjie Yuan on Jun 4 Tsinghua University Authors: , , , , , , , , Abstract FiRe-OPD improves on-policy distillation in large language models…
…Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains (2026) SOD: Step-wise On-policy Distillation for Small Language Model Agents (2026) Multi-Rollout On-Policy Distillation via Peer Successes…
…Co-Design to support low-latency rollout generation on server and consumer-grade hardware for real-world observation-action-feedback loops. Experiments on embodied world-model , long-horizon, and action-policy benchmarks…
…We convert a bidirectional video generator into a few-step autoregressive world model using causal forcing , DMD-style distillation , and long-rollout training . Training on self-generated long-horizon contexts exposes the…
…Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models (2026) The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems (2026) State-Dependent Safety Failures in Multi-Turn Language Model Interaction (2026…
…it diagnoses rollout-level evidence , revises diagnostics , backtests interventions, and accumulates reusable skills . Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human…