MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
Webshaper: Agentically data synthesizing via information-seeking formalization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
ViDR treats source figures as retrievable and verifiable evidence objects in multimodal deep research reports and introduces MMR Bench+ to measure improvements in visual integration and verifiability.
MindDR combines a Planning Agent, DeepSearch Agent, and Report Agent with SFT cold-start, Search-RL, Report-RL, and preference alignment to reach competitive scores on research benchmarks using 30B-scale models.
citing papers explorer
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence
ViDR treats source figures as retrievable and verifiable evidence objects in multimodal deep research reports and introduces MMR Bench+ to measure improvements in visual integration and verifiability.