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

Recursive Self-Improvement of AI Research Agents

The paper explores recursive self-improvement in AI research agents, where an AI system autonomously enhances its own code through iterative optimization. AIDE^2, a system implementing this process, discovered multiple improvements in an 8-day run, including new search policies and memory mechanisms, with results generalizing across various benchmarks and demonstrating reduced reward hacking.

Open original
SIGNAL FROM THE SOURCE
2
source votes
Tracking sinceSeptember 23, 20262 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 22, 2026Dhruv Srikanth, Bingchen Zhao, Dixing Xu
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.

2 source votes

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

WHY IT MAY MATTER

This research demonstrates how AI systems can autonomously enhance their own efficiency, leading to improvements in diverse tasks and reducing unintended behaviors like reward hacking without explicit optimization.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily 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.

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.

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.

2 days agoDaily Papers

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

CodeMidas is an agentic pipeline that converts implemented functionality in open-source codebases into executable reinforcement learning (RL) environments using only source code as input. It generates 5,545 training tasks from 3,185 codebases across 23 languages and 15 domains, improving performance on multiple coding benchmarks when training MiMo-V2.5 with GRPO.

5 days agoDaily Papers

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

This paper introduces FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from sparse, unordered partial point clouds. The model uses a Multi-state Articulation Transformer to aggregate articulation cues across multiple observations and an observed articulation span objective to supervise motion ranges of parts.

6 days agoDaily Papers

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

The paper introduces OmniVChat, a task involving native audio-visual dialogue where models process audio and video inputs directly without separate text. It presents OmniVChat-Studio for generating dialogues, OmniVChat-Bench for evaluation, and OmniVChat-RL for reinforcement learning, improving performance on both synthetic and real-world data.

5 days ago