Context switching to GitHub just to ship an agent-generated PR breaks developer flow. You can now manage the full PR lifecycle inside Omnigent: • Merge PRs or toggle auto-merge • Edit titles & markdown descriptions inline • Assign labels & request reviewers • Post comments Everything stays in the Pull Requests tab next to your active session. 🔗 Details: #Omnigent#

Context matters more than the emoji itself. That is the central finding of a new study led by PKU HSBC Business School's Assoc. Prof. Ye Weiming, published in the International Journal of Advertising. Across two experiments with 535 participants, the study found that emojis undercut luxury branding in public advertising while enhancing warmth and satisfaction in one-on-one customer service. The takeaway for marketers: distance in public, closeness in private. #Pekonomist#

"Context Language Models" Most agents rely on an external harness to manage context. This paper instead lets the model directly rewrite its own context as a file, learning when to compress, delete, preserve, or reorganize information. At zero-shot, it gets 11.4% higher BrowseComp-Plus accuracy with 21.5% fewer FLOPs, and RL further improves the context-management policy.

Context is all you need. At Apsara Conference 2026, Yusen Chen, VP of Alibaba Group and CEO of QwenWork, shared why enterprise AI needs to understand a company’s data and how it works, not just perform tasks.

Context is all you need. At #ApsaraConference2026#, Yusen Chen, VP of Alibaba Group and CEO of QwenWork, shared why enterprise AI needs to understand a company’s data and how it works, not just perform tasks. Explore more: #AgenticEra# #AgentNative# #AIAgentsAtApsara# #BringYourAgent# #AlibabaCloud#

// ContextLeak in AI Agents // The whole attack surface here is a tool name and a tool description. Stealing an LLM agent's runtime context, meaning the user prompt, the execution trajectory and the tool list, needs three things to line up. The agent has to pick the malicious tool, it has to pass its context in as arguments, and the tool has to forward that anywhere the attacker wants. Existing work covers the first and third conditions and leaves the second one mostly alone. ContextLeak targets the middle step. Researchers at Duke use an attack LLM to generate the malicious tool's name and description, then fine-tune that LLM with reinforcement learning on a set of shadow users with diverse simulated agent contexts. The reward functions are built specifically for the exfiltration objective. It remains highly effective when the shadow contexts differ substantially from the victim's, and it outperforms existing malicious-tool attacks adapted to this setting. Paper: Chat with Paper: