The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents

Sasank Annapureddy; Anjaneya Prasad Thamatani

cs.AISep 26, 2026

The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents

Authors: Sasank Annapureddy, Anjaneya Prasad Thamatani

Organizations: All experiments in this program were designed, executed, and adversarially verified by the PRIMA multi-agent research-and-verification system [1] under the authors’ direction.

Abstract

Long-horizon LLM agents must convert accumulated experience into durable memory, deciding what to keep, compress, abstract into reusable skills and rules, or forget. We report a four-phase research program on this consolidation problem whose central finding is a shift in what is measured: from how much an agent remembers, to whether its consolidation decisions are any good, to whether those decisions can be trusted. Phase 1 learns episodic boundaries from agent traces by downstream utility; an honest near-miss (oracle correlation 0.691 vs a 0.70 bar) whose lasting output is a three-gate anti-leakage protocol. Phase 2 learns when to promote experience and to which abstraction level under a token budget, achieving a verified +22.7% task-success improvement with 7x compression, but exposing a degenerate-forgetting failure and a distribution-shift failure mode we name lambda-prevalence coupling. Phase 3 introduces ConsolidationBench, an oracle-by-construction benchmark that scores consolidation decisions against a known optimum on three non-circular axes; production retrieval systems retain information yet score zero on cross-level transfer. Phase 4 introduces governed consolidation: the decision wrapped in poison-resistance, reversibility, and auditability guarantees with a quality gate. Governance is statistically distinct from the quality score ( $r^2 = 0.43$ ; partial $r = 0.27$ ; identical-quality policies differ threefold in governance), so the contribution survives independently of the metric's external validity. On that question we report a resolved negative: after a graded-reuse redesign removed a structural ceiling, a two-benchmark study with 2,532 real answer cells finds the quality score does not predict real transfer accuracy (pooled Spearman $ρ= -0.24$ , n = 12, CI spanning zero). An adversarial self-critique pass cleared the final claim set with zero surviving overclaims.

Figures & tables

Method	Boundary F1	Oracle Corr.	Task Success	Proc. Reuse
Oracle	1.000	1.000	0.900	0.691
BoundaryLearner	0.808	0.691	0.679	0.535
Bayesian Surprise	0.895	0.315	0.705	0.554
Fixed Interval	0.622	0.235	0.641	0.508

Table 1: Phase 1 held-out results (best checkpoint by validation F1).

Policy	Success	RetN	Compression	Transfer	CQS 0	CQS
fixed_L2 (best)	0.303	0.480	7.40 $\times$	0.233	0.336	0.585
learned_policy	0.368	0.582	7.37 $\times$	0.167	0.291	0.552
mem0_style	0.335	0.531	7.43 $\times$	0.000	0.000	0.159
simplemem_style	0.306	0.485	7.53 $\times$	0.000	0.000	0.152
fixed_L1	0.274	0.434	7.47 $\times$	0.000	0.000	0.144
retrieval_only	0.265	0.418	7.36 $\times$	0.000	0.000	0.141

Table 2: ConsolidationBench leaderboard, medium configuration (oracle ceiling: success

0.632

, transfer

0.333

). Eight of ten policies score

\textsc{CQS}_{0}{}=0

for zero transfer; the retrieval-augmentation systems (Mem0-style, SimpleMem-style) retain well yet generalize nothing. The graded CQS (final column) separates the zero-transfer policies by retention without changing the transfer finding. RetN

=

oracle-normalized retention.

Guarantee	Measurement	Medium	Hard
G1 Poison-resistance	false rules admitted	0	0
G2 Reversibility	rollback recovery (0 $\to$ 1 contrast)	1.0	1.0
G3 Auditability	ledger completeness	1.0	1.0
G4 Quality gate	CQS 0 retained	0.622	0.475

Table 3: Governed-consolidation verdicts (both configurations). G1: false rules admitted from planted poison decoys. G2: rollback recovery on the temporal-contradiction variant. G3: ledger completeness over all promotions. G4: the quality gate, scored under CQS 0 (the form in use when Phase 4 ran). All criteria are pre-registered; all met.

Phase	What the adversarial pass caught / enforced
1	Anti-leakage protocol established (provenance, probe, count-matched gates); the detector’s near-miss reported as a negative, not rounded up.
2	Degenerate forgetting exposed (high precision via near-total inaction); $\lambda$ –prevalence coupling root-caused; integrity gates re-passed.
3	Headroom gate (benchmark sensitivity proven before training); non-circularity verified ( $\|r\|\leq 0.59$ ); a $k$ -sweep sensitivity correction and three overclaims (leaderboard-champion wording, oracle-gap size, stale non-circularity values) caught and fixed.
4	Governance-by-inaction exploit caught (forced the mandatory G4 binding); G2’s constructed-variant ease hedged; a tie-handling statistical error in the validity $\rho$ caught and corrected; $17$ claims, zero surviving overclaims, three hedges.

Table 4: Per-phase adversarial-verification outcomes. Each phase’s claims were attacked by an independent verification pass; the table reports what it caught.

Memory Consolidation for LLM Agents

See all 18 papers

May 13, 2026

Useful Memories Become Faulty When Continuously Updated by LLMs

Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated abstractions distilled across many episodes into reusable, schema-like lessons. Recent agentic-memory systems pursue the consolidated form: an LLM rewrites past trajectories into a textual memory bank that it continuously updates with new interactions, promising self-improving agents without parameter updates. Yet we find that such consolidated memories produced by today's LLMs are often faulty even when derived from useful experiences. As consolidation proceeds, memory utility first rises, then degrades, and can fall below the no-memory baseline. More surprisingly, even when consolidating from ground-truth solutions, GPT-5.4 fails on 54% of a set of ARC-AGI problems it had previously solved without memory. We trace the regression to the consolidation step rather than the underlying experience: the same trajectories yield qualitatively different memories under different update schedules, and an episodic-only control that simply retains those trajectories remains competitive with the consolidators we test. In a controlled ARC-AGI Stream environment that exposes Retain, Delete, and Consolidate actions, agents preserve raw episodes by default and double the accuracy of their forced-consolidation counterparts; disabling consolidation entirely (episodic management only) matches this auto regime. Practically, robust agent memory should treat raw episodes as first-class evidence and gate consolidation explicitly rather than firing it after every interaction. Looking forward, reliable agentic memory will require LLMs that can consolidate without overwriting the evidence they depend on.

Dylan Zhang, Yanshan Lin, Zhengkun Wu +4

University of Illinois Urbana-Champaign · IIIS, Tsinghua University

AI Agent Reliability Persistent Memory for Language Models Episodic Memory Agent Memory Management LLM Agent Reliability Memory Consolidation+2

Ask PDF

Jun 23, 2026

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. Existing memory agents actively update external memory through generated write, revise, and delete operations, but these updates may omit important information, corrupt existing memory, or introduce unsupported hallucinated content. Once stored, such errors become persistent system-state failures that can affect future reasoning and generation. In this paper, we propose TrustMem, a framework designed to improve the trustworthiness of memory consolidation. TrustMem relies on a Memory Transition Verifier to evaluate the transition process of memory updates in terms of coverage, preservation, and faithfulness. It further constructs preference pairs among candidate updates under the same memory state, enabling preference-guided reinforcement learning to directly optimize memory updating behaviors. Extensive experiments demonstrate that TrustMem improves both memory utility and reliability: it achieves state-of-the-art results across MemoryAgentBench, HaluMem, and the Mem-alpha validation set, improves HaluMem memory extraction by 12.14 F1 points, and reduces transition-level omission, corruption, and hallucination by 40.1%, 79.1%, and 50.0%, respectively, compared with the strongest baseline for each error type.

Tianyu Yang, Sudipta Paul, Vijay Srinivasan +2

AI Center-Mountain View, Samsung Electronics · University of Notre Dame

LLM Agent Memory Memory Consolidation for LLM Agents Agent Memory Management LLM Agent Reliability

Ask PDF

May 15, 2026

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents

Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every incoming interaction for memory extraction, and such an eager memory consolidation scheme leads to substantial token consumption. To tackle this problem, we propose RecMem by rethinking when memory consolidation should be conducted. RecMem stores incoming interactions in a subconscious memory layer and encode them using lightweight embedding models for retrieval. LLMs are only invoked to extract episodic and semantic memory when sustained recurrence are observed for semantically similar interactions. Such recurrence-based consolidation works because these interactions correspond to a semantic cluster with rich information and thus are worth extraction and summarization. To improve accuracy, RecMem also incorporates a semantic refinement mechanism that recovers the fine-grained facts omitted by memory extraction. Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.

Zijie Dai, Shiyuan Deng, Sheng Guan +4

Department of Computer Science and Engineering, The Chinese University of Hong Kong · Huawei Cloud · School of Computer Science, Beijing University of Posts and Telecommunications +2

Long-Horizon LLM Agents Agent Memory Management Memory-Augmented Language Model Agents Persistent Memory for Language Models Memory Consolidation Memory Management for LLM Agents+1

Ask PDF

Abstract

Memory Consolidation for LLM Agents

Explore similar work

Useful Memories Become Faulty When Continuously Updated by LLMs

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents