Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when it hurts.
The paper proposes a training‑free detector that uses sentence‑level context sensitivity to identify unsupported content in retrieval‑augmented generation (RAG) answers. By re‑scoring each sentence with full context, no context, and each chunk removed, the method flags the chunk whose removal most reduces a sentence’s likelihood as the likely source. Evaluated on RAGTruth, TofuEval, and RAGBench, the detector outperforms answer‑level faithfulness scores, achieving AUCs up to 0.745 and matching per‑chunk fact‑checkers while using only a fraction of the compute required by large‑language‑model judges.
By Mohamed Aly Bouke
arXiv:2608. 11775v1 Announce Type: new Abstract: Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood.
By Nicholas E. Kyrkewood
arXiv:2609.37469v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without...
By Suting Chen, Peichun Hua, Yunming Xiao
arXiv:2608. 04569v1 Announce Type: cross Abstract: Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget.
By Zhengpei Hu, Kai Li, Dapeng Fu, Xuechao Zou, Yuanhao Tang, Yue Li, Tengfei Cao, Jianqiang Huang
Long‑horizon LLM agents use context compaction to replace an overflowing interaction history with a natural‑language summary. The paper shows that these summaries mix factual environment data with the compressor’s reasoning, making it hard for the agent to distinguish the two. The authors introduce Source‑Judged Compaction (SJC), a training‑free post‑processing step that scores each summary entry for a source in the environment or previous summary and removes unsupported entries, improving cross‑run reliability by 2.1%–8.9% on AppWorld and OfficeBench without increasing token usage.
By Guanghui Min, Chen Chen
The paper investigates how conversational Retrieval-Augmented Generation (RAG) benchmarks that rely on relevance judgments to determine context sufficiency can be misleading. By re‑running official baselines on the RETECO track and evaluating with both large‑language‑model judges and a blind audit, the authors show that stronger retrievers produce a higher proportion of contexts lacking gold documents yet still containing the answer, leading to a sharp drop in shortcut precision from 0.68 to 0.10. The study demonstrates that many false misses arise from hard negatives, gold content from other turns, or neighboring chunks, and that using retrieval scores alone as a sufficiency detector can underestimate answerability by up to 0.19 in AUROC.
By Ivan Kochergin, Vasily Konovalov
The paper investigates whether the object selected in a grounded language‑model pipeline actually reaches the reader, a failure that can break the handoff between stages. By auditing 600 HybridQA questions across three selector families, the authors find that exact key lookup and title matching recover the selected object in all 1,463 resolvable records, but body‑only BM25 omits it in 26.6% of cases at cutoff five, while hybrid retrieval with reranking omits it only 1.0%. The study also shows that misalignment between selected and retrieved objects can reduce exact match scores by up to 31 points, and introduces the Returned‑Object Profile (ROP) as a tool for reproducible auditing.
By Siddharth Vohra, Runmin Jiang, Xiaomo Li, Min Xu
The paper introduces EAR, an Entity‑Aware Partitioning approach that improves retrieval‑augmented generation for multiple‑choice question answering by extracting normalized surface anchors from questions, answers, and the corpus. EAR retrieves local windows around matching anchors and can attach a larger parent passage via an extractive summary, reducing retrieved words by 37.5‑40.2% compared to fixed‑size chunks. Experiments on a cleaned MMLU‑style subset with Mistral, Gemma, and DeepSeek show modest accuracy changes, none statistically significant, highlighting EAR’s methodological contribution of compact, inspectable retrieval units.
By Cenab Batu Bora, Oylum Alatl{\i}, Sebnem Bora, Oguz Dikenelli
The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.
By Nusrat Jahan Lia, Aritra Mazumder
Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation. We investigate whether verbalized confidence from black-box language models can serve as an actionable signal for retrieval routing.
arXiv:2607. 04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why.
By Mohamed Aly Bouke