norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers2 hours ago
ResearchDaily Papers

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

The paper introduces RetireOPD, a method for agentic reinforcement learning that uses self-retiring on-policy distillation. It optimizes a skill-conditioned teacher with environment rewards and trains a skill-free student with RL and OPD, allowing the student to stop using the teacher when performance stabilizes. RetireOPD improves success rates in ALFWorld and WebShop tasks compared to a baseline RL approach.

Open original
SIGNAL FROM THE SOURCE
4
source votes
Tracking sinceSeptember 18, 20264 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 17, 2026Yan Yu, Zhengxi Lu, Yizhou Liu
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

4 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

RetireOPD allows the student agent to autonomously stop using the teacher once it reaches a stable performance level, potentially reducing reliance on external supervision in reinforcement learning tasks.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

LynnReal-Omni: Native Multi-Modal Video Generation for Agentic Visual Workflows

LynnReal-Omni is a native multimodal video generation framework that combines text-to-video, image-conditioned generation, and structural control into a single model. It includes a 32B shared multimodal diffusion transformer and a 27B Flash version for real-time rendering, with a data pipeline and evaluation method designed for video generation tasks.

4 days agoDaily Papers

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

LimiX-2 is a new model in the LimiX family that uses the Contextual Mechanism Networks (CMNs) paradigm, pretrained with Context-Conditional Masked Modeling (CCMM). It focuses on learning joint representations of data generation processes rather than target-centric prediction, showing superior performance on tabular data benchmarks and promoting causal awareness.

3 days agoDaily Papers

StepAudio 3 Realtime Technical Report

StepAudio 3 Realtime is an audio-language foundation model designed for real-time spoken interaction, featuring a continuous listen-converse-think-act loop. It includes Deep Perception for interpreting user intent, Seamless Duplex for handling audio stream synchronization, and Think-While-Speaking to balance reasoning and latency. The model achieves high performance on benchmarks like MMSU and Artificial Analysis Full-Duplex, along with a task-success rate on τ-Voice.

6 days agoDaily Papers

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

PhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.

4 days agoDaily Papers

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

The paper introduces XConf, a method for estimating confidence in language models by leveraging the model's accumulated experience. XConf uses past episodes, including tasks, reflections, confidence levels, outcomes, and lessons learned, to inform current confidence estimates through a recall and reflect process. It outperforms existing methods in discrimination and calibration with lower computational cost.

3 days agoDaily Papers

ScienceIDE: Turning the World's Scientific Codebase into Agent Learnable Environments

The paper introduces ScienceIDE, a framework that transforms scientific code repositories into programmable environments for training scientific agents. These environments enable task generation, execution, and verification, supporting supervised fine-tuning and reinforcement learning. The approach demonstrates improvements in scientific code repair and general-purpose benchmarks.

2 days ago