REVIEW 8 cited by
A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system that increases effective context length up to 20x in our experiments. Inspired by how humans interactively read long documents, we implement ReadAgent as a simple prompting system that uses the advanced language capabilities of LLMs to (1) decide what content to store together in a memory episode, (2) compress those memory episodes into short episodic memories called gist memories, and (3) take actions to look up passages in the original text if ReadAgent needs to remind itself of relevant details to complete a task. We evaluate ReadAgent against baselines using retrieval methods, using the original long contexts, and using the gist memories. These evaluations are performed on three long-document reading comprehension tasks: QuALITY, NarrativeQA, and QMSum. ReadAgent outperforms the baselines on all three tasks while extending the effective context window by 3.5-20x.
Forward citations
Cited by 8 Pith papers
-
MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents
Reconstructing the exact model invocation state for each sampled action, instead of flattening the whole interaction, lets teacher distillation guide compact-memory agents without state mismatch.
-
Is Progressive Disclosure All You Need for Long-Context Agents?
Progressive disclosure is redundant for a strong agent reading one book, but decisive when an agent must navigate a 20-book library; one flat routing level beats deeper hierarchies.
-
AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
A benchmark comparing five memory strategies for conversational agents on three public datasets finds dense vector retrieval alone maintains long-range recall, at roughly 25 times the token cost of recency windows.
-
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
AgentKVShift corrects all reused KV cache entries in agentic memory by estimating a chunk-level residual offset from a small probe set, recovering near-fresh accuracy at 10–30% recompute ratios.
-
StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
StoryBench introduces a branching interactive-fiction benchmark with immediate-feedback and self-recovery modes, and shows that current LLMs fail at long-term memory tasks, especially self-correction.
-
Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
An agentic reasoning framework that adds web search, code execution, and knowledge-graph memory to an LLM, boosting performance on expert-level benchmarks close to proprietary deep research systems.
-
Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
H-MEM organizes LLM agent memory into a four-level semantic hierarchy with pointer-based coarse-to-fine retrieval, improving average LoCoMo QA scores over five baselines while cutting retrieval cost.
-
A Novel Self-Evolution Framework for Large Language Models
A dual-phase framework that uses a Censor satisfaction scorer to expand training data and then applies SFT plus frequency-weighted DPO, reporting benchmark gains over SFT, PO, and memory baselines.
Discussion (0). Continue with ORCID to comment.