17 papers
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Siyuan Huang, Pengyu Cheng, Haotian Liu +10
LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task…
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
Mubashara Akhtar, Anka Reuel, Prajna Soni +36
Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult…
REKEY: Metadata-Grounded Visual-Key Regeneration for Contamination-Resilient VQA Evaluation
Tengjie Lin, Yutao Sun, Jingwei Ni +7
Static visual question answering (VQA) benchmarks age quickly: Once the items leak into training corpora, scores can reflect memorization rather than genuine visual ability, thus o…
GDPO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
Haotian Liu, Yihao Liu, Jingwei Ni +11
As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorith…
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
Vladislav Smirnov, Chieu Nguyen, Sergey Senichev +14
Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via m…
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Jingwei Ni, Yihao Liu, Xinpeng Liu +7
Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually authoring such skills does not scale, and skills generated purely from parametric knowle…