norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers1 hour ago
ResearchDaily Papers

ACLArena: Agent Continual Learning in Multi-stage Post-training

The paper introduces ACLArena, a framework for studying Agent Continual Learning (ACL) by analyzing mechanisms of forgetting and generalization at the model and token levels. It compares methods like multi-teacher distillation and model merging, proposing a new ACL approach that combines offline replay with a routed network of RL-specialized LoRA experts, showing effectiveness in multi-domain learning.

Open original
SIGNAL FROM THE SOURCE
4
source votes
Tracking sinceSeptember 22, 20264 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 21, 2026Haixin Wang, Xiaoxuan Wang, Junkai Zhang
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

This research provides a structured approach to improve agents' ability to retain and acquire knowledge across multiple training stages, which is crucial for industrial applications requiring diverse capabilities.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily 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.

6 days agoDaily Papers

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

The paper identifies a problem called Value Flattening in Proximal Policy Optimization (PPO) critics, where estimated state values change sharply while critic predictions remain flat. It introduces SP^3O, a method that applies value loss to only a few states per response, showing improvements in policy learning.

6 days agoDaily Papers

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

This paper evaluates the ability of the MiniMax-H3 multimodal generative model to reason about the physical world. The study introduces a new framework for assessing physical reasoning through four dimensions, using tasks that require integrating information across multiple modalities. The model achieves an overall success rate of 41.97% across 517 evaluation instances, with video-based reasoning performing best and audio-based reasoning least effectively.

6 days agoDaily Papers

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

IntBMoE introduces a block-conditioned Mixture-of-Experts (MoE) framework that decouples participation, execution, and materialization by combining dense expert composition with sparse block execution. It uses a learned codebook for blocks and a hypernetwork to merge experts, achieving full participation while keeping execution and memory costs low. Experiments show improvements in image classification, language modeling, and sequential recommendation, with real-world deployment in AMap's recommendation system.

4 days agoDaily Papers

Self-Evolving Search Index

The paper introduces SELF-INDEX, a framework that enables an index to self-evolve without human intervention by autonomously diagnosing retrieval issues, revising index keys, and validating changes. It also uses a Query Simulator to proactively explore new retrieval demands, improving performance across various corpora and downstream applications.

5 days agoDaily Papers

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

The paper introduces Document Retrieval-Aware Chunking (D-RAC), a method for efficiently processing enterprise documents by normalizing them into PDF and converting them into retrieval-optimized Markdown using a multimodal LLM. This approach preserves document structure, reduces token costs, and improves chunking efficiency compared to traditional methods.

yesterday