…ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints (2026) From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs (2026) Affordance Agent Harness: Verification-Gated Skill…
…Recent structured approaches have further advanced this paradigm by organizing inference across multiple trajectories, refinement rounds, and verification-based feedback. However, existing structured test-time scaling methods either weakly coordinate parallel reasoning…
…Before any pairwise comparison, ARR externalizes a VLM 's internalized preference knowledge as prompt-specific rubrics , translating holistic intent into independently verifiable quality dimensions. This conversion of implicit preference structure into inspectable…
…A Hierarchical Benchmark for Visual Website Development with Agent Verification (2026) WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing (2026) Test-Driven AI Agent Definition (TDAD): Compiling Tool…
…Across two Qwen3 architectures/scales ( MoE Qwen3-30B-A3B, dense Qwen3-4B) and both in-domain ( AIME25 ) and out-of-domain ( GPQA-Diamond ) benchmarks, SxS improves accuracy--content-latency Pareto trade-offs…
…Evolutionary Verification (2026) TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration (2026) EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation (2026) SkillLearnBench: Benchmarking Continual Learning…
…On three agentic benchmarks under strict privacy settings, PAAC dominates the Pareto frontier of privacy and accuracy, improving average accuracy by 15-36\% and reducing average leakage by 2-6times over state…
…Understanding and Fixing Aggregation Bias in GRPO Published on Apr 14 Submitted by zhiyuan zeng on May 8 OpenMOSS Authors: , , , , , , , , , , Abstract Balanced Aggregation improves reinforcement learning with verifiable rewards by addressing optimization…
…Generative Multimodal Reward Modeling via Joint Planning and Verification (2026) Visual Preference Optimization with Rubric Rewards (2026) ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning (2026) Leveraging Verifier-Based Reinforcement Learning…
…On downstream mathematics and general reasoning benchmarks, more expressive training settings yield both larger performance gains (up to +10.66 points) and more compute-efficient transfer compared to less expressive settings, demonstrating…