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

From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

The paper introduces Trace2Env, a learning-free framework that uses historical interaction traces to create a reusable environment worldbook for simulating realistic environments without rebuilding the original system. It improves next-observation fidelity and long-horizon interaction consistency compared to conventional prompt-based language world models.

Open original
SIGNAL FROM THE SOURCE
98
source votes
Tracking sinceOctober 9, 202698 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedOctober 5, 2026Quanyu Long, Xiao Chen, Jianda Chen
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.

98 source votes

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

WHY IT MAY MATTER

This approach enables realistic environment simulation without requiring access to the original system, useful for training and evaluating LLM agents in scenarios where the original environment is unavailable.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

The paper investigates on-policy distillation (OPD) in cross-tokenizer settings, focusing on alignment coverage and supervision reliability. It finds that strict 1:1 token alignment covers most student-generated tokens despite vocabulary mismatches, and that restricting reverse KL to a top-16 subset of shared vocabulary achieves comparable accuracy to full shared-vocabulary OPD, while adding span supervision reduces accuracy.

3 days agoDaily Papers

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

CheckerBench is a benchmark for evaluating coding agents' ability to synthesize static-analysis checkers from defect specifications, including tasks derived from 300 CVEs across multiple repositories and language ecosystems. CheckerLab, an evaluation framework, measures diagnostic contrast, patch localization, and tool use, with results showing that current agents struggle to develop reliable checkers, achieving a maximum Pass@1 of 45.33%.

3 days agoDaily Papers

Tetris3D: 3D Scene Generation With Objects That Fit Together

Tetris3D is a generative framework for 3D scene reconstruction from a single image, ensuring objects are geometrically and physically coherent. It uses explicit conditioning on surrounding objects' geometry and physical relationships, along with a physics-based dataset called ComOb for training and evaluation.

2 days agoDaily Papers

NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis

NAMVIS is a diffusion-free framework for multi-view image synthesis that uses geometry-conditioned next-scale autoregression, predicting discrete visual tokens through coarse-to-fine scale steps and parallel sampling across target views. It outperforms diffusion-based methods in PSNR, SSIM, and LPIPS while being over three times faster.

6 days agoDaily Papers

SGF+: Decoupling Gradient Flows for Autoregressive Video Generation

The paper introduces SGF+, a method for autoregressive video generation that decouples the roles of denoising and context writing by assigning separate parameters to each, improving visual quality and temporal consistency without additional training data or longer training periods.

2 days agoDaily Papers

Q-Learning with Scalar Adjoint Matching

The study presents Q-Learning with Scalar Adjoint Matching (SQAM), a method that uses scalar adjoint to enhance fine-tuning of flow policies in off-policy RL. The method shows significant improvements in challenging OGBench tasks.

2 days ago