II · Planning & Control FlowEmerging★

Rumination Agent

also known as 沉思, Rumination Loop, Long-Horizon Research Loop, Hypothesis-Revising Agent

Run a single agent through a protracted think-search-verify-revise-act loop spanning hundreds of tool calls, autonomously re-formulating hypotheses across the run.

Context

A team runs an agent on open-ended research and deep-investigation work — assessing whether a paper's claims replicate, tracing the root cause of a system anomaly, scoping a novel question — where the answer cannot be reached by a short reason-act-observe loop or by a one-shot plan. The agent has retrieval, browsing, and code-execution tools and is expected to spend minutes to hours on a single question, accumulating evidence across hundreds of tool calls.

Problem

Short reasoning budgets and one-shot plans collapse these investigations into surface-level answers because the agent never gets to revisit its working hypothesis. Splitting the work across multiple agents (a lead researcher delegating to subagents) introduces coordination overhead, message-passing artefacts, and inconsistent reasoning across the team. A single agent that runs for hours without any explicit cycle structure either declares victory too early or wanders into unbounded looping, with no checkpoint where drift becomes visible. The team needs one agent with an explicit, repeatable cycle that can sustain a long investigation without losing coherence or runaway cost.

Forces

  • Depth of investigation requires many sequential tool calls, but long traces bloat context and degrade attention.
  • Re-formulating hypotheses mid-run is essential for hard questions, yet uncontrolled re-formulation is indistinguishable from drift.
  • A single agent avoids inter-agent message-passing overhead, but loses the natural checkpoints a multi-agent split provides.
  • The loop must be long-running but not unbounded; termination criteria are domain-dependent.

Example

A user asks an agent to assess whether a recent paper's empirical claims hold up. The agent forms an initial hypothesis (claim is supported), then over forty cycles searches for replications, reads supplementary materials, runs small reproductions in a sandbox, narrows the hypothesis to one specific table, eventually flips to claim is partially supported with one figure non-reproducible, and writes the verified findings into a structured report. No subagents are spawned; the same model carries the thread end-to-end.

Diagram

Solution

Therefore:

Each outer iteration runs five named phases: (1) think — emit an updated working hypothesis given the trace so far; (2) search — issue retrieval, browsing, or tool calls scoped to that hypothesis; (3) verify — check the new evidence against the hypothesis with explicit pass/fail notes; (4) revise — either narrow, broaden, or replace the hypothesis based on verification; (5) act — write findings, update an externalised plan, or commit an artefact. The loop terminates on confidence threshold, budget exhaustion, or explicit answer-ready signal. Context is compacted between cycles by replacing prior search dumps with verified-evidence summaries, so the trace stays linear in cycles, not in tool calls.

What this pattern forbids. The agent must not branch into parallel sub-investigations, must not skip the verify phase before revising the hypothesis, and must not extend the run past the declared cycle or token budget without explicit budget-extension authorisation.

The smaller patterns that complete this one —

  • generalisesReAct★★— Interleave a single thought, a single tool call, and a single observation per step so the agent reasons over fresh evidence.

And the patterns that stand alongside it, or against it —

  • complementsExtended Thinking★★— Spend a configurable budget of internal reasoning tokens before producing a user-visible answer.
  • alternative-toLead Researcher★★— A lead agent writes a research plan and dispatches parallel sub-agents that fan out for breadth-first information gathering, then merges results.
  • conflicts-withUnbounded Loop✕— Anti-pattern: run the agent loop without a step budget and let model self-termination decide.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

References

Provenance