5 papers
CompassPlay: Rewarding the Proposer for Where It Moves the Solver
Sophia Xiao Pu, Ximeng Sun, Jiang Liu +4
In self-play, a proposer generates verifiable tasks to train a solver. Proposer rewards often depend on the solver's success rate, but equally difficult tasks can differ in their t…
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
Sophia Xiao Pu, Yumo Xu, Sailik Sengupta +5
Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retaining it whole or discarding it…
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu +14
Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stal…
Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
Sophia Xiao Pu, Zhaotian Weng, Chengzhi Liu +4
Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning…
Dynamic Evaluation for Oversensitivity in LLMs
Sophia Xiao Pu, Sitao Cheng, Xin Eric Wang +1
Oversensitivity occurs when language models defensively reject prompts that are actually benign. This behavior not only disrupts user interactions but also obscures the boundary be…