관심도 점수
100
- 검색 slug
- openai-codex
- 실제 연결
- Hacker News, GitHub, arXiv
- 키워드
- the, and, for, codex, code, openai, agent, agents
- 마지막 수집
- 2026-07-25T10:47:33.243Z
출처별 탭
OpenForgeRL: Train Harness-native Agents in Any Environment
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with open infrastructure, whose SFT/RL stacks cannot natively express stateful, multi-process harness inference. To address this, we present OpenForgeRL, an open-source framework for training harness-based agents end-to-end in diverse environments. OpenForgeRL achieve...
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction. Using OpenAI's gpt-5.6-sol model alias, we test 25 pre-specified mirrored trade-off profiles. Direct exposure to an objective authorizing concealment, fabrication, and pressure produced advice net opposed to its target. After an Id and Censor transformed the same objective into affect and a constraint-rewritten, target-bearing intention, the user-facing Superego---...
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests
AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools. Coding agents inherit security risks from both the LLM backbone, where adversarial prompts, poisoned training data, and backdoor triggers can cause models to emit insecure or attacker-chosen code, and their agentic architecture, where tool-using autonomy enables induced misuse of external APIs, data exfiltration, and persiste...
Multi-Source and Cross-Scenario Strategy-Guided Code Optimization
Automated code optimization improves program performance by refactoring source code, and recent studies use LLMs to generate optimization patches. The newest approaches are strategy-guided: they summarize strategies from historical optimization commits as static analysis rules, and use these rules to match code locations for LLMs to optimize. However, these approaches have two limitations: (1) the strategies may come from other knowledge sources, such as textbooks and web pages, but the existing approaches cannot...
When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets
Shippers are beginning to delegate carrier selection to large language model (LLM) agents. We ask what such delegation does to a freight matching market, and which platform design choices contain it. We carried out agent-based simulations in which fifty shipper agents, built on commercial LLMs from OpenAI (GPT), Anthropic (Claude), and Google (Gemini), procure truckload capacity for thirty days. The market implements the rules of digital freight matching: each load is offered down the shipper's ranked list of carr...
The Černý Conjecture for One-Cluster Automata via Annular Spectral Descent
We prove the Černý conjecture for synchronizing one-cluster automata. More precisely, let a synchronizing automaton with state set $Q$, $|Q|=n$, have a letter $a$ whose functional digraph has a unique cycle $C$ of length $m$, and let $\ell$ be the least nonnegative integer for which $a^\ell$ maps $Q$ onto $C$. Assume $\ell\ge1$. For every nonempty proper subset $S\subset C$, we prove that there is a word $w$ of length at most $n$ such that $wa^\ell$ maps more than $|S|$ states of $C$ into $S$. This proves the posi...
BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance
As pathogen genomic surveillance scales, the bottleneck is shifting from data generation to analysis. We present BioSecBench-Surveillance, a verifiable benchmark of 100 evaluations testing whether AI agents can infer the right analysis pipeline from raw sequencing data and surveillance context. Each evaluation gives an agent only the data and context a human analyst would have, then grades its structured answer deterministically. The tasks span seven categories, from taxonomic classification to genetic-engineering...
Keeping the Cache Warm Pays: Keepalive Economics for Agentic Workloads
Frontier LLM providers cache a prompt's processed prefix so that a follow-up request sharing it pays ~10% of the input price and skips most of the prefill latency. Agentic workloads systematically destroy this benefit: the agent sends a request, runs a tool or waits for approval for minutes, and by the time the follow-up is sent the cached prefix has been evicted, so the agent pays the full prefill again. A client-side keepalive, replaying the prefix on a timer during the pause, prevents this, and it is individual...
A counter-example to Batyrev's conjecture on the non-negativity of stringy Hodge numbers
Batyrev's conjecture on the non-negativity of stringy Hodge numbers has been a fundamental open problem, guiding and motivating many beautiful mathematical results in motivic integration, mirror symmetry, and the McKay correspondence. We give a counter-example to Batyrev's conjecture which was discovered with the assistance of OpenAI's ChatGPT.
Measuring Reward-Seeking via Contrastive Belief Updates
Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure because a model that pursues the grader's judgment and one that pursues the intended objective behave identically whenever the grader rewards the intended behavior. We measure reward-seeking using Contrastive Synthetic Document Finetuning to change a model's beliefs about what the grader rewards, putting those beliefs in conflict with what...
openai/codex-plugin-cc
Use Codex from Claude Code to review code or delegate tasks.
diegosouzapw/OmniRoute
Never stop coding. Free MIT AI gateway: one endpoint, 290+ providers (90+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 500+ contributors
HKUDS/nanobot
Lightweight, open-source AI agent for your tools, chats, and workflows.
Wei-Shaw/sub2api
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
code-yeongyu/oh-my-openagent
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
NousResearch/hermes-agent
The agent that grows with you
router-for-me/CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model through API
asgeirtj/system_prompts_leaks
Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT GPT-5.6, Codex GPT-5.6, GPT-5.5. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.
openai/codex
Lightweight coding agent that runs in your terminal
zhayujie/CowAgent
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)