Perplexity Agent API launches Wide Research

// 1h agoPRODUCT UPDATE

Perplexity Agent API launches Wide Research

Perplexity has launched the "Wide Research" preset for its Agent API to automate complex, multi-step search and reasoning tasks. Operating asynchronously, the preset allows developers to submit research prompts, poll for completion, and download citation-backed collections.

// ANALYSIS

Perplexity is moving up the value chain from offering raw search results to providing structured, managed research-as-a-service. By handling the complex multi-step search orchestration, reasoning, and citation verification in a single API call, this API dramatically lowers the barrier to building autonomous web-research agents.

–Managed Complexity: Eliminates the need for developers to design custom multi-agent loops and paginated search architectures.
–Native Asynchrony: Using background polling is the right architectural choice for minutes-long research tasks, aligning well with agent-based app development.
–Hallucination Risk: The success of the API hinges on citation accuracy and preventing hallucinated listings, which remains the key challenge for long-running agent workflows.

// TAGS

perplexity-agent-apiwide-researchai-searchdevtool

DISCOVERED

1h ago

2026-07-14

PUBLISHED

2h ago

2026-07-14

RELEVANCE

8/ 10

AUTHOR

AravSrinivas

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE22m ago

Vercel adds Seedream 5.0 Pro to AI Gateway

Vercel has announced the integration of Bytedance's Seedream 5.0 Pro image generation model into its AI Gateway. Developers can now easily utilize this model using the generateImage function within the Vercel AI SDK, expanding the multimodal capabilities readily available in the Vercel ecosystem.

NEWS56m ago

Superapp launches native iOS AI builder

Entrepreneur Marc Lou revealed he abandoned plans to build an iOS version of Lovable, celebrating Vitalik Kotik's success in launching the native iOS AI builder Superapp. Kotik's achievement in native mobile AI generation recently earned Superapp an advertising spot on TrustMRR.

RESEARCH1h ago

Direct-OPD bypasses expensive reinforcement learning by distilling policy shifts from small teacher models to stronger students.

Direct-OPD (Direct On-Policy Distillation) is a novel method for weak-to-strong generalization that addresses the high computational cost of Reinforcement Learning with Verifiable Rewards (RLVR) in large language models. Rather than running resource-intensive RL from scratch on larger models or performing naive policy distillation (which carries over teacher biases), Direct-OPD extracts the RL-induced policy shift of a smaller teacher model by taking the log-ratio of its post-RL and pre-RL checkpoints. This log-ratio serves as a dense, implicit on-policy reward signal to guide the training of the stronger student model. The method significantly reduces rollout costs while demonstrating competitive reasoning capabilities and support for sequential policy shift compositions.