LoHoSearch is a new benchmark of 544 KG-constructed questions across 11 domains where the strongest search agent scores 34.74% and context strategies add at most 6.8%.
super hub
Cohen and Ruslan Salakhutdinov and Christopher D
103 Pith papers cite this work, alongside 739 external citations. Polarity classification is still indexing.
103
Pith papers citing it
739
external citations · Crossref
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
claims ledger
- dataset 88 + TG-Norm 47.24 50.17 22.68 52.40 46.27 + TG-Norm +D t-rescaling 47.94 50.54 22.77 52.00 46.71 + TG-Norm +D t-rescaling + Ada-Clipping(A 2TGPO) 49.42 51.29 25.21 53.60 48.06 both training and evaluation. Seven open-domain question answering benchmarks are used, or- ganized into two groups by reasoning depth.Multi-hopbenchmarks consist of HotpotQA [ 28], 2WikiMultihopQA [29], MuSiQue [30], and Bamboogle [31].Single-hopbenchmarks consist of Natural Questions (NQ) [ 32], TriviaQA [ 33], and PopQ
- dataset requiring no additional compressor or compression-specific training (distinct from latent-compression approaches [11]). We find that small values such as Lp ∈ {3,5,7} substantially reduce MaxSim cost while preserving the shared-representation design. 4 Benchmarks and Experimental Setup We evaluate INTRA on four Wikipedia-based QA benchmarks: HotPotQA [38], 2WikiMultihopQA [12], MuSiQue [34], and Natural Questions [19]. Together they span bridge and comparison reasoning, cleaner two-hop evidence
- background query involves chaining together multiple related facts across entities, CTI reports, or time (e.g., actor → uses → malware → targets → sector, or comparing campaigns over time). Dense retrieval that returns the top-𝑘 most relevant text chunks [20, 22] can fail when evidence is distributed across distant text fragments, when constraints must be satisfied jointly, or when the answer depends on chaining multiple facts [ 40]. Equally important, LLM-based CTI assistants must reliably abstain when th
- background Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (eds.),Advances in Neural Information Processing Systems, 2022. URLhttps://openreview.net/forum?id=R9KnuFlvnU. [69] Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. τ-bench: A benchmark for tool-agent-user interaction in real-world domains, 2024.URL https://arxiv. org/abs/2406.12045, 2024. [70] Junjie Ye, Guanyu Li, Songyang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Tao Ji, Qi Zhang, Tao Gui, and Xua
authors
co-cited works
representative citing papers
Cortex uses an Ontological Corpus Graph to structure web-scale corpora, creating a refined 24.14B-token corpus and a new benchmark validated on eight LLMs.
FAPO automates LLM pipeline optimization via iterative diagnosis and prompt-or-structure edits, beating GEPA baseline by +14.1 pp mean across 18 comparisons and +33.8 pp when structural changes occur.
LatentSkill uses a hypernetwork to generate LoRA adapters from textual skills, enabling weight-space storage that cuts prefill tokens and boosts agent success rates on ALFWorld and Search-QA.
LazyAttention kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV cache reuse, delivering 1.37× lower TTFT and 1.40× higher throughput than Block-Attention under skewed document distributions while preserving output quality.
MemTrain introduces two coupled self-supervised proxy tasks on Wikipedia corpora to train general context-memory capabilities in LLMs, reporting gains of up to 17.67 points on long-text and search-based QA benchmarks over direct post-training.
Defines cost-aware RAG with evidence cost tiers and shows static selectors are brittle while agentic LLM-based selection is promising but model-dependent.
GrepSeek introduces a two-stage trained agent that uses shell commands for direct corpus search, achieving the strongest token-level F1 and Exact Match on seven open-domain QA benchmarks.
LiveBrowseComp shows search agents rely on intrinsic knowledge on standard benchmarks, with scores dropping 25-40 points and closed-book accuracy below 2% on questions about facts from the prior 90 days.
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
Tool schema compression by 44-50% enables agentic RAG at 8K context where uncompressed schemas fail, with +20.5 pp exact match lift across models and scaling to over 800 tools.
Latent Cache Flow uses a small joint-translation-and-compression adapter to let LLMs with different contexts exchange KV cache summaries, outperforming both larger C2C adapters and text in early experiments.
HexAGenT reduces the SLO scale required for timely agentic LLM workflow completion by an average of 20.1% at 95% attainment and 33.0% at 99% attainment on heterogeneous A100/H100/H200 clusters.
F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
SIOP enables turn-level credit assignment in LLM agents via semantic clustering of final answers as latent outcomes, improving performance on reasoning benchmarks without verifiers.
SENECA uses a novel self-consistent missing mass calculation to improve discrete entropy estimates in small-sample regimes and outperforms alternatives in numerical tests.
ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
SOB benchmark shows LLMs achieve near-perfect schema compliance but value accuracy of only 83% on text, 67% on images, and 24% on audio.
A controlled formal language task reveals fine-tuning outperforms in-context learning on in-distribution generalization but equals it on out-of-distribution, with ICL showing greater sensitivity to model size and tokenization.
Language models frequently violate temporal scope stability in multi-turn dialogues by drifting toward present-day assumptions even when they possess the correct facts.
Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
Semantic stratification organizes documents into entity-based clusters to systematically generate queries for missing strata, yielding formal coverage guarantees and interpretable failure mode visibility in retrieval evaluation.
PTR framework profiles a workflow upfront then executes it deterministically with bounded verification and repair, limiting LM calls to 2-3 while outperforming ReAct in 16 of 24 tested configurations.
HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.
citing papers explorer
-
LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
LiveBrowseComp shows search agents rely on intrinsic knowledge on standard benchmarks, with scores dropping 25-40 points and closed-book accuracy below 2% on questions about facts from the prior 90 days.
-
Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents
PTR framework profiles a workflow upfront then executes it deterministically with bounded verification and repair, limiting LM calls to 2-3 while outperforming ReAct in 16 of 24 tested configurations.
-
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
Misleading tool feedback produces value inversion in LLM agents, with performance dropping below matched no-feedback baselines on HotpotQA and similar tasks.
-
InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain
InfoMem is an answer-conditioned information gain reward for RL training of long-context memory agents that improves performance when applied to successful trajectories and normalized.
-
RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering
RASER routers built on one-shot RAG features selectively escalate retrieval, matching SOTA F1 scores on multi-hop QA while using 41-49% of the tokens required by always-prune across six LLMs and three benchmarks.
-
TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
TriLens detects hallucinations via per-layer entropy trajectories of logit-lens readouts from three internal modules across LLMs and QA benchmarks.
-
Automatic Layer Selection for Hallucination Detection
FEPoID automatically selects optimal or near-optimal intermediate layers for hallucination detection across LLM architectures and tasks, outperforming prior criteria and baselines, with an added truncation step that further improves performance.
-
ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
ICRL uses joint RL training of solver and critic with distribution-calibration re-weighting and role-wise advantage estimation to internalize critique into unassisted LLM performance, yielding 6.4-point gains on agentic tasks and 7.0 on math reasoning with Qwen3 models.
-
CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
Joint RL training of reasoning agent and document ranker via GRPO with semantic grouping and composite rewards yields consistent gains over fixed-retrieval baselines on seven QA benchmarks.
-
Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval
A hybrid graph-text retrieval system for cyber threat intelligence improves multi-hop question answering by up to 35% over vector-based RAG on a 3,300-question benchmark.
-
Atomic Task Graph: A Unified Framework for Agentic Planning and Execution
ATG maintains explicit DAGs of subtasks to enable dependency tracking, parallel execution, and localized repair in LLM agents, outperforming baselines on three benchmarks with 7B-8B models.
-
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Introduces PACT protocol that projects agent outputs into action-state records, yielding comparable or better task performance with substantially fewer tokens in multi-agent LLM systems and production harnesses.
-
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
An agentic harness letting the LLM self-manage flat text-file storage via tool calls outperforms eight prior memory systems on cross-scenario generality across QA, chat, trajectory, stress-test, and long-horizon tasks.
-
DenseSteer: Steering Small Language Models towards Dense Math Reasoning
DenseSteer is an inference-time steering framework that improves small LLMs' accuracy on math reasoning by modulating representations toward dense reasoning patterns with fewer but higher-density steps.
-
An Information-Geometric Framework for Stability Analysis of Large Language Models under Entropic Stress
A thermodynamic-inspired information-geometric framework defines a composite LLM stability score that outperforms a utility-entropy baseline by 0.0299 on average across 80 observations, with gains increasing at higher entropy.
-
KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models
KnowledgeBerg is a 4,800-question, 17-language benchmark showing LLMs fail at systematically enumerating bounded knowledge universes and performing compositional set-based reasoning over them.
-
Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage
Strict generation directly from Task-Method-Knowledge models yields 96.5% grounded and 92.6% usable QA pairs across 23 topics, outperforming transcript-first and TMK-aware alternatives on representational grounding.
-
Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG
TGS-RAG adds graph-to-text re-ranking with global voting and text-to-graph orphan path bridging to improve precision and efficiency in multi-hop RAG over prior baselines.