Agentic RL Daily

VOL. 032

8 research signals

DAILY EDITION / SAVED SNAPSHOT

Daily Signals: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it chal

A dated Agentic RL Daily snapshot with 8 verified primary-source signals across papers, official releases, deployment evidence, and safety or alignment findings.

EDITOR'S VIEW

Three judgments

  1. The edition is based only on primary sources or official project releases.
  2. Older signals remain visible as continuing observations, not as rewritten news.
  3. Headline claims are constrained by the evidence included in this dated snapshot.

FULL EDITION

All signals in this edition

Archived / 2026-08-18

01

PapersPapers

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it chal

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it chal

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Training Algorithms
arXiv ->

02

PapersPapers

Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration. However, existing work has raised questions about how LLMs actually balance exploration and exploitation. Unlike classical agents, LLM agents engage with

Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration. However, existing work has raised questions about how LLMs actually balance exploration and exploitation. Unlike classical agents, LLM agents engage with

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Agent Capabilities
arXiv ->

03

PapersPapers

This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making. The tasks and reward functions are designed such that temporal info

This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making. The tasks and reward functions are designed such that temporal info

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Agent Capabilities
arXiv ->

04

PapersPapers

Satellite agents for on-orbit navigation tasks need to predict collision risks using limited onboard observations. However, conventional planners often rely on predefined maps and fixed environmental assumptions, limiting their adaptability in dynamic on-orbit scenarios. In this paper, we propose Or

Satellite agents for on-orbit navigation tasks need to predict collision risks using limited onboard observations. However, conventional planners often rely on predefined maps and fixed environmental assumptions, limiting their adaptability in dynamic on-orbit scenarios. In this paper, we propose Or

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Agent Capabilities
arXiv ->

05

PapersPapers

Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs.

Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs.

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Agent Capabilities
arXiv ->

06

PapersPapers

Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through complex harnesses remains largely unexplored, as scaling such training to long-horizon agent tasks introduces fundamental cha

Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through complex harnesses remains largely unexplored, as scaling such training to long-horizon agent tasks introduces fundamental cha

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Agent Capabilities
arXiv ->

07

PapersPapers

Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what constitutes a "good" explanation? In this work, we evaluate explanations through the lens of counterfactual simulatability-whether the explanation is useful

Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what constitutes a "good" explanation? In this work, we evaluate explanations through the lens of counterfactual simulatability-whether the explanation is useful

A verified papers signal preserved from the original daily snapshot. The primary source is linked for full context, while the archive keeps the original publication date and source attribution intact.

Agent Capabilities
arXiv ->

08

Open SourceOpen Source

verl-project/verl v0.9.0

verl-project/verl v0.9.0

官方来源补充信号：# v0.9.0 ## Highlights ### Training #### Megatron - DeepSeek-V4 GRPO end-to-end with Megatron-Bridge actor/ref, vLLM rollout and FP8/MXFP4 weight transfer (#6473), plus a contiguous context-parallel layout (#7221) and CP fixes that make long-context DeepSeek-V4 runnable (#7297). - [Megatron Lite (`mlite`)](https://verl.readthedocs.io/en/latest/advance/megatron_lite_backend.html) backend for DeepSeek-V4, GLM-5 and Kimi-K2.5/K2.6, with 256-GPU GRPO launchers (#6791, #7091). - Muon optimizer support via Megatron-Core `TensorParallelMuon`, with AdamW fallback for non-2D params and an opt-in `muon_

Training AlgorithmsSystems Engineering记忆与自进化评估体系
GitHub ->