norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers3 hours ago
ResearchDaily Papers

MIMESIS: Learning User Simulators as Training Environments for Interactive Agents

The paper introduces MIMESIS, a user simulator trained on human conversations with explicit reasoning supervision and 13 realistic behavioral patterns. It achieves a SOUL-Index of 65.7, outperforming existing models. The simulator is used to train agents through multi-turn reinforcement learning, showing better generalization than GPT-5.5. The paper also proposes Coached On-Policy Self-Distillation (CSD) to improve agent performance using simulator-generated feedback.

Open original
SIGNAL FROM THE SOURCE
9
source votes
Tracking sinceOctober 8, 20269 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedOctober 7, 2026Hoang Phan, Dat Huynh, Andrey Zhmoginov
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.

9 source votes

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

WHY IT MAY MATTER

MIMESIS provides a scalable and realistic alternative to human user interactions for training and evaluating interactive agents, improving behavioral fidelity and generalization. The Coached On-Policy Self-Distillation method enhances agent performance through detailed feedback from the simulator.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily 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%.

2 days agoDaily Papers

Gains and Collapse in On-Policy Distillation: A Reinforcement Learning Perspective

The paper explores on-policy distillation (OPD) in language model post-training, explaining how it can lead to either performance gains or generation collapse. It suggests that OPD amplifies student behaviors favored by the teacher's implicit feedback, and proposes methods like masking unhealthy responses and SFT initialization to mitigate collapse.

6 days agoDaily Papers

World Action Learning via Interaction-Centric Spectral Latent Guidance

The paper introduces WING, a framework that transfers interaction knowledge from human egocentric videos to robot policies by separating observer-induced motion from hand-object interactions and using spectral analysis to identify shared temporal structures between human and robot behaviors. It achieves high success rates on multiple benchmarks and demonstrates strong performance in real-world tasks.

6 days agoDaily Papers

Native Action-Prior Learning from Videos for World Action Models

The paper introduces NAVA-WAM, a method for pretraining action policies directly from observation-only videos without relying on action-annotated robot data. It uses two stages: first, pretraining on videos with visual transition supervision, and second, post-training with action-labeled demonstrations to improve robot control.

6 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.

yesterdayDaily 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.

2 days ago