Agentic RL Daily

VOL. 014

8 research signals

DAILY EDITION / SAVED SNAPSHOT

Daily Signals: Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation

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 / 2026-07-31

01

PapersPapers

Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation

Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation

An agent playing a Nash-equilibrium strategy in a two-player zero-sum imperfect-information game secures the game value but forfeits the additional value offered by a flawed opponent. Diffuse deviations pose a particular challenge: binary release rules may gather too little evidence to act, while a

Training AlgorithmsAgent CapabilitiesData Loops安全与对齐
arXiv ->

02

PapersPapers

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the task instruction is central to CUA evaluation, data curation, and reinforcement learning. Neither human-written verifie

Reward and Credit AssignmentAgent CapabilitiesData Loops安全与对齐评估体系
arXiv ->

03

PapersPapers

ORCA-bench: How Ready Are Language Model Agents for Oncall?

ORCA-bench: How Ready Are Language Model Agents for Oncall?

Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchm

Agent CapabilitiesSystems Engineering评估体系
arXiv ->

04

PapersPapers

MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems

MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems

Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation. However, existing systems typically treat communication topology as a fixed design choice or an offline optimization tar

Training AlgorithmsAgent Capabilities记忆与自进化评估体系
arXiv ->

05

PapersPapers

MemHarness: Memory Is Reconstructed, Not Replayed

MemHarness: Memory Is Reconstructed, Not Replayed

Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the agent's cur

Training AlgorithmsAgent CapabilitiesData Loops记忆与自进化
arXiv ->

06

PapersPapers

Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs

Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs

Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challenging. While recent studies show that inference-time scaling can improve frontier c

Agent CapabilitiesData Loops评估体系
arXiv ->

07

PapersPapers

How Benchmarks Mis-Score Computer-Use Agents

How Benchmarks Mis-Score Computer-Use Agents

Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A score is the output of a pipeline in which tasks can be stale, trajectories can omit decisive visual evidence, evaluators

Agent CapabilitiesData Loops评估体系
arXiv ->

08

PapersPapers

Agentic Method for Deterministic Validation of Legacy Code Migration

Agentic Method for Deterministic Validation of Legacy Code Migration

Migration of legacy COBOL programs to Java requires extensive testing to ensure correct functionality. This effort is often complicated by the lack of test data and the difficulty of validating all corner cases. In this paper we propose a novel agentic test-synthesis method, the "Locksmith Loop," wh

Agent Capabilities
arXiv ->