…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…
…Evaluated on SpreadsheetBench Verified and WikiTableQuestions, SkillGrad consistently outperforms training-based skill evolution baselines across two backbone LLMs, improving over the strongest training-based baseline by 6.7 percentage points on average…
…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…
…performance across multiple benchmarks. AI-generated summary Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step…
…Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench , a 2,049-item benchmark for industrial procurement QA in Chinese, grounded in Chinese national standards…
…Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD (2026) CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026) Please give a…
…An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech (2026) Language-Invariant Multilingual Speaker Verification for the TidyVoice 2026 Challenge (2026) Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual…