Search: “7b”

2 stories in the last 3d

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

SeverityAll critical 0 high 0 medium 0 low 0 info 3

Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking

MERIT-Rank integrates multiple LLM reasoning trajectories for text reranking; its 4B model outperforms most 7B and 32B rerankers on BRIGHT.

MERIT-Rank formulates a Multi-Trajectory Reasoning Space that evaluates query-document relevance from multiple perspectives and consolidates reasoning paths with a joint reranker. A progressive training framework, Progressive Rank Policy Optimization (PRPO), stabilizes reasoning trajectories while improving ranking quality through staged objectives. Experiments on reasoning-intensive and traditional retrieval benchmarks show consistent gains over competitive baselines, with the 4B model outperforming most 7B and even 32B rerankers on BRIGHT.

arXiv cs.AI / cs.LG / cs.CLSep 17, 12:24 UTC · 1d agoAI research

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

RetireOPD adds self-retiring on-policy distillation to agentic RL, boosting Qwen2.5 agent success on ALFWorld by 14-19% and WebShop by 12-19%.

RetireOPD first optimizes a decoupled, skill-conditioned teacher with environment rewards, then trains a skill-free student jointly with RL and on-policy distillation, retiring the teacher adaptively once student-teacher discrepancy stops shrinking. Across Qwen2.5 models from 1.5B to 7B, it improves ALFWorld success rate by 14.1-18.8% and WebShop accuracy by 11.8-19.0% over RL baselines. The student surpasses its own skill-conditioned teacher in every tested setting.

Hugging Face daily papersupdated Sep 17, 17:52 UTC · 20h agofirst Sep 16, 20:00 UTC · 1d agoAI research 2 sources