VOL. 020
8 research signalsDAILY EDITION / SAVED SNAPSHOT
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
FULL EDITION
Archived / 2026-08-06
01
ContextWeave: A Real-World Workflow Benchmark
Memory is essential as language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to retrieval or question answering.
02
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
AI-supported care planning can help clinicians, patients, caregivers, and care teams coordinate complex decisions across clinical, functional, psychosocial, and environmental needs.
03
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems.
04
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
Defensive driving scores are useful only when they preserve distinctions between policies that observe surrounding actors and those that do not.
05
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated.
06
EviGraph: Evidence-Guided Autonomous Research Agents
Autonomous research agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between research questions, experiments, results, and conclusions.
07
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''.
08
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt.