A proposer-solver agent pair achieves supervised-level video temporal grounding and fine-grained captioning from 2.5K unlabeled videos via self-reinforcing evolution.
Defining and characterizing reward gaming,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PROGRS uses outcome-conditioned centering on PRM scores to safely integrate process rewards into GRPO for improved Pass@1 on math benchmarks.
citing papers explorer
-
EvoGround: Self-Evolving Video Agents for Video Temporal Grounding
A proposer-solver agent pair achieves supervised-level video temporal grounding and fine-grained captioning from 2.5K unlabeled videos via self-reinforcing evolution.
-
LLM Reasoning with Process Rewards for Outcome-Guided Steps
PROGRS uses outcome-conditioned centering on PRM scores to safely integrate process rewards into GRPO for improved Pass@1 on math benchmarks.