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

Coding Agents for Generalized Task and Motion Planning Problems

This paper explores the use of coding agents to automate task and motion planning (TAMP) by generating programs that generalize across problem instances. The agents, using large language models like Claude Code (Opus 5) and Codex (GPT-5.6 Sol and GPT-6 Astra), outperformed traditional planners and baselines in simulated environments with varying object counts, showing higher success rates and lower computational costs.

Open original
SIGNAL FROM THE SOURCE
3
source votes
Tracking sinceSeptember 25, 20263 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 24, 2026Matteo Merler, Bowen Li, Josh Roy
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.

3 source votes

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

WHY IT MAY MATTER

This research demonstrates that coding agents can effectively handle generalized TAMP tasks, offering a promising approach for automated planning in complex environments with varying object configurations.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

The paper introduces Taste-Bench, a benchmark for evaluating an agent's 'taste' in making long-horizon decisions. It measures the ability to choose the better path in decision forks without knowing future outcomes, revealing that current models perform poorly and that taste can be improved through distillation.

3 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.

4 days agoDaily Papers

HappyWorld-Bench: Evaluating the Reliability of World Models Under Interaction

HappyWorld-Bench is a comprehensive benchmark for evaluating the reliability of generated worlds under interaction, exploring their consistency and responsiveness. It includes three tracks—video, spatial, and embodied world models—with 1,138 video prompts, 300 spatial scenes, and 254 embodied test cases. The benchmark uses human A/B comparisons and automated metrics to assess behavioral correctness and model performance across 14 video, 9 spatial, and 8 embodied systems.

4 days agoDaily Papers

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

This paper introduces an all-in-one multilingual scene text recognition system that uses a script-aware Mixture-of-Experts (MoE) architecture. The system, called ScriptMoE, outperforms existing methods on multilingual text recognition tasks by leveraging a large synthetic dataset and a lightweight architecture that shares a visual encoder while using script-specific experts for decoding.

4 days agoDaily Papers

OmniEdu: Open Foundation Models for Learning and Teaching

OmniEdu is an open family of foundation models designed for K-12 education, focusing on problem solving, curriculum understanding, diagnostic reasoning, and instructional support. The models are trained on a diverse dataset of educational resources and evaluated on multiple benchmarks, showing strong performance in educational tasks.

6 days agoDaily Papers

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

The paper introduces Spatial-Interactor, a framework for training vision-language models (VLMs) to model physical-world state transitions through interaction. It uses a three-level curriculum and a dataset of simulated and real interaction trajectories to improve spatial reasoning in dynamic environments.

6 days ago