22 papers
Recompute or Reuse? Diagnosing and Mitigating Textual Shortcuts in VLM Self-Reflection
Wenxiao Fan, Jingling Fu, Fang Li +9
Vision-language models (VLMs) are expected to revise their reasoning when visual evidence changes. Failures to do so are often attributed to insufficient visual attention or contex…
Learning More from Less: Unlocking Internal Representations for Benchmark Compression
Yueqi Zhang, Jin Hu, Shaoxiong Feng +9
The prohibitive cost of evaluating Large Language Models (LLMs) necessitates efficient alternatives to full-scale benchmarking. Prevalent approaches address this by identifying a s…
Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL
Chuyi Tan, Peiwen Yuan, Xinglin Wang +8
Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data. Reinforce…
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
Xinglin Wang, Hao Lin, Shaoxiong Feng +9
Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing par…
Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning
Danyang Liu, Kan Li
Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these bound…
On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
Xinglin Wang, Zishen Liu, Shaoxiong Feng +9
Agentic systems increasingly solve complex user requests by executing orchestrated workflows, where subtasks are assigned to specialized models or tools and coordinated according t…