arXiv Computer Vision
Long-MDR: Long-Context Reinforcement Learning for Multimodal Deep-Research Agents
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 27
Boosting Reasoning in Large Multimodal Models via Activation Replay
The paper introduces Activation Replay, a training‑free method that improves reasoning in post‑trained large multimodal models (LMMs) by replaying low‑entropy activations from the base model’s input context. It shows that Reinforcement Learning with Verifiable Rewards (RLVR) shifts low‑entropy activations and that modulating these activations enhances reasoning across tasks such as mathematics, visual agents, and video reasoning. Experiments demonstrate that Activation Replay outperforms alternatives like high‑entropy replay or direct cross‑model intervention, boosting Pass@K and broadening RLVR’s reasoning coverage.
arXiv Computer Vision
6d ago
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
MMSearch-OPD is a new approach for long‑horizon multimodal search agents that combines a controllable data refinement pipeline with joint reinforcement learning and on‑policy distillation. The refinement process expands reasoning chains from existing simple multimodal questions, allowing adjustable search depth and cross‑modal evidence requirements while reusing image–question pairs. Training uses answer rewards, behavior penalties, and a decaying distillation coefficient to guide the agent, and experiments demonstrate that both data refinement and joint training after supervised fine‑tuning improve long‑horizon multimodal search performance.
arXiv AI
Oct 15
Neos: Learning to Interleave Search and Visual Reasoning
arXiv:2610.17043v1 Announce Type: new Abstract: Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still struggle to convert intermediate visual eviden...
arXiv AI
Sep 25
Pistis Technical Report
The Pistis Technical Report introduces the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5. The models are developed through a scalable post‑training framework that begins with large‑scale multimodal supervised fine‑tuning and then applies Interleaved Distillation and Reinforcement Learning (IDRL) to integrate on‑policy distillation and reinforcement learning within a single training loop. Two specialized variants—Pistis‑Thinking for deep multimodal reasoning and Pistis‑Agentic for long‑horizon planning, iterative reasoning, and tool use—are produced at both scales, and a system‑level method called Pistis‑Auto‑Harnessing (PAH) further improves inference harness performance without updating model parameters.
arXiv Computation and Language
Aug 21
SPyCE: Skill-Policy Co-evolution for Multimodal Agents
arXiv:2607. 13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps.
arXiv Computation and Language
Sep 21
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
arXiv:2609.20844v1 Announce Type: new Abstract: Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over tim...