AgentClinic is a multimodal agent benchmark demonstrating that LLM diagnostic accuracy on MedQA drops to below one-tenth in sequential clinical simulations, with Claude-3.5 leading and large tool-use differences across models.
hub Canonical reference
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Canonical reference. 89% of citing Pith papers cite this work as background.
78
Pith papers citing it
89
external citations · Pith
Background
89% of classified citations
abstract
Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad hoc approach that augments LMs with retrieval of relevant knowledge, decreases such issues. However, indiscriminately retrieving and incorporating a fixed number of retrieved passages, regardless of whether retrieval is necessary, or passages are relevant, diminishes LM versatility or can lead to unhelpful response generation. We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) that enhances an LM's quality and factuality through retrieval and self-reflection. Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens. Generating reflection tokens makes the LM controllable during the inference phase, enabling it to tailor its behavior to diverse task requirements. Experiments show that Self-RAG (7B and 13B parameters) significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks. Specifically, Self-RAG outperforms ChatGPT and retrieval-augmented Llama2-chat on Open-domain QA, reasoning and fact verification tasks, and it shows significant gains in improving factuality and citation accuracy for long-form generations relative to these models.
hub tools
citation-role summary
background 16
baseline 1
method 1
citation-polarity summary
representative citing papers
MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
Leyline adds a policy-directed KV cache edit primitive with closed-form RoPE correction for agentic inference, reporting +11.2 pp cache-hit lift and +14.3 pp solve-rate gain.
LogDx-CI benchmark shows hybrid grep+tail reducers achieve top diagnosis quality at low cost, agent loops shrink quality variance across reducers, and cross-family LLM summarizers outperform same-family pairs.
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.
HDRI is a six-principle eight-stage framework for hypothesis-organized LLM research featuring gap-driven iteration, traceable fact reasoning, and subject locking, realized in INFOMINER with reported gains in fact density and completeness.
AdaGATE improves evidence F1 scores on HotpotQA for multi-hop RAG under clean, redundant, and noisy conditions by framing selection as gap-aware token-constrained repair, outperforming baselines while using 2.6x fewer tokens.
TADI shows that domain-specialized tools orchestrated by an LLM over dual structured and semantic databases can convert heterogeneous wellsite data into evidence-grounded drilling intelligence, with tool design mattering more than model scale.
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
Quantile tokens inserted into LLM inputs combined with neighbor retrieval enable direct prediction of full distributions, yielding lower MAPE and narrower intervals than baselines on Airbnb and StackSample tasks.
IG-Search computes step-level information gain rewards from policy probabilities to improve credit assignment in RL training for search-augmented QA, yielding 1.6-point gains over trajectory-level baselines on multi-hop tasks.
ROZA graphs enable self-improving RAG by storing evidence-specific reasoning chains, yielding up to 10.6pp accuracy gains and 46% lower cost through graph traversal feedback.
DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.
AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoning robustness on five benchmarks.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
Cheaper LLM judges match frontier models on citation-quality F1 but differ substantially in false positive and false negative rates, meaning reward signal calibration matters more than model cost.
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
MemStrata maintains temporal validity in retrieval memory via deterministic (s,r,o) supersession, matching RAG on static recall while reaching 0.95-1.00 accuracy on evolving knowledge where RAG scores 0.20-0.47 and cutting stale-fact errors from 15-40% to near zero.
GDP-RAG targets only information deltas in multi-hop RAG through preliminary grounding, gap-conditioned prompts, and skeletal trajectories, reaching 60.63% accuracy at 0.51 cost-of-pass on HotpotQA, 2WikiMultiHopQA, and MuSiQue.
The Novelty-Aware Research Agent layers query analysis, ReAct retrieval, ranking, schema-guided extraction, three-pass comparison, and answer generation on RAG to produce structured comparison artifacts that standard RAG cannot.
Introduces soft-target attention probing for pre-generation estimation of LLM per-prompt hallucination probability, with a proof that the soft label is the unique unbiased minimum-variance estimator and empirical gains over linear probing and binary labels on QA tasks.
BioInsight is a multi-agent orchestration system that converts disease-associated protein tables into interactive evidence dashboards with typed artifact contracts, improving reported traceability and ranking over baselines given the same retrieved evidence.
citing papers explorer
-
AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments
AgentClinic is a multimodal agent benchmark demonstrating that LLM diagnostic accuracy on MedQA drops to below one-tenth in sequential clinical simulations, with Claude-3.5 leading and large tool-use differences across models.
-
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
MemTrace shows that evidence utilization, not retrieval, is the dominant failure mode in LLM long-term memory systems across tested configurations.
-
Leyline: KV Cache Directives for Agentic Inference
Leyline adds a policy-directed KV cache edit primitive with closed-form RoPE correction for agentic inference, reporting +11.2 pp cache-hit lift and +14.3 pp solve-rate gain.
-
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
LogDx-CI benchmark shows hybrid grep+tail reducers achieve top diagnosis quality at low cost, agent loops shrink quality variance across reducers, and cross-family LLM summarizers outperform same-family pairs.
-
Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets
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.
-
Hypothesis-Driven Deep Research with Large Language Models: A Structured Methodology for Automated Knowledge Discovery
HDRI is a six-principle eight-stage framework for hypothesis-organized LLM research featuring gap-driven iteration, traceable fact reasoning, and subject locking, realized in INFOMINER with reported gains in fact density and completeness.
-
AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation
AdaGATE improves evidence F1 scores on HotpotQA for multi-hop RAG under clean, redundant, and noisy conditions by framing selection as gap-aware token-constrained repair, outperforming baselines while using 2.6x fewer tokens.
-
TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
TADI shows that domain-specialized tools orchestrated by an LLM over dual structured and semantic databases can convert heterogeneous wellsite data into evidence-grounded drilling intelligence, with tool design mattering more than model scale.
-
OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
OCR-Memory encodes agent trajectories as images with visual anchors and retrieves verbatim text via locate-and-transcribe, yielding gains on long-horizon benchmarks under strict context limits.
-
RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
-
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context
Quantile tokens inserted into LLM inputs combined with neighbor retrieval enable direct prediction of full distributions, yielding lower MAPE and narrower intervals than baselines on Airbnb and StackSample tasks.
-
IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
IG-Search computes step-level information gain rewards from policy probabilities to improve credit assignment in RL training for search-augmented QA, yielding 1.6-point gains over trajectory-level baselines on multi-hop tasks.
-
ROZA Graphs: Self-Improving Near-Deterministic RAG through Evidence-Centric Feedback
ROZA graphs enable self-improving RAG by storing evidence-specific reasoning chains, yielding up to 10.6pp accuracy gains and 46% lower cost through graph traversal feedback.
-
DOTRAG: Retrieval-Time Reasoning Along Paths
DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.
-
AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation
AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoning robustness on five benchmarks.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution
Cheaper LLM judges match frontier models on citation-quality F1 but differ substantially in false positive and false negative rates, meaning reward signal calibration matters more than model cost.
-
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
Explicit bank, retrieval, and QA state roles reduce ghost-memory failures on conflict-heavy LTP and improve some temporal scores on LoCoMo, with host-dependent gains.
-
Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
-
Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge
MemStrata maintains temporal validity in retrieval memory via deterministic (s,r,o) supersession, matching RAG on static recall while reaching 0.95-1.00 accuracy on evolving knowledge where RAG scores 0.20-0.47 and cutting stale-fact errors from 15-40% to near zero.
-
Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
GDP-RAG targets only information deltas in multi-hop RAG through preliminary grounding, gap-conditioned prompts, and skeletal trajectories, reaching 60.63% accuracy at 0.51 cost-of-pass on HotpotQA, 2WikiMultiHopQA, and MuSiQue.
-
Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning
The Novelty-Aware Research Agent layers query analysis, ReAct retrieval, ranking, schema-guided extraction, three-pass comparison, and answer generation on RAG to produce structured comparison artifacts that standard RAG cannot.
-
Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing
Introduces soft-target attention probing for pre-generation estimation of LLM per-prompt hallucination probability, with a proof that the soft label is the unique unbiased minimum-variance estimator and empirical gains over linear probing and binary labels on QA tasks.
-
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
BioInsight is a multi-agent orchestration system that converts disease-associated protein tables into interactive evidence dashboards with typed artifact contracts, improving reported traceability and ranking over baselines given the same retrieved evidence.
-
Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.
-
Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
Grounded Decoding fuses full-RAG and retrieval-only next-token distributions via normalized geometric mean from a KL-barycenter to improve factual consistency and citation quality in RAG.
-
STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media
Stream mines streaming media to create and release StreamDial, a dataset of 87,498 structured task-oriented dialogue sessions across automotive, restaurant, and hotel domains using persona construction, Conversational Blueprints, and RAG.
-
EVE-Agent: Evidence-Verifiable Self-Evolving Agents
EVE-Agent adds an evidence verifier to the proposer-solver loop that rewards spans by marginal accuracy gain, producing self-generated but inspectable training examples for search agents.
-
Mem-$\pi$: Adaptive Memory through Learning When and What to Generate
Mem-π is a framework using a dedicated model and decision-content decoupled RL to generate context-specific guidance on demand for LLM agents, outperforming retrieval baselines by over 30% on web navigation.
-
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
H-Mem introduces a hybrid tree-plus-graph memory mechanism that evolves short-term agent memories into long-term summaries and enables efficient retrieval, reporting state-of-the-art QA results on three benchmarks.
-
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
Mutual Reinforcement Learning allows heterogeneous LLMs to exchange experience through mechanisms like Peer Rollout Pooling, Cross-Policy GRPO Advantage Sharing, and Success-Gated Transfer, with outcome-level sharing identified as favorable on the stability-support trade-off.
-
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
-
FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning
FT-RAG introduces a fine-grained graph-based retrieval framework for tables plus a new 9870-pair benchmark, reporting 23.5% and 59.2% gains in table- and cell-level hit rates and 62.2% higher exact-value recall over baselines.
-
Evolve: A Persistent Knowledge Lifecycle for Small Language Models
A 2B model using Evolve reaches 60-84% accuracy on 750 queries across specialist questions, NaturalQuestions, and TriviaQA (up from 20-33%) while cutting teacher invocations by over 50% via a consolidated section-based knowledge store.
-
The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
HEG-TKG grounds LLM clinical reasoning in hierarchical evidence-based temporal knowledge graphs from 4,512 PubMed records, delivering 100% citation verifiability and error detectability where standard RAG and unprompted LLMs produce none.
-
Preregistered Belief Revision Contracts
PBRC is a contract protocol that enforces evidential belief updates in deliberative multi-agent systems and proves it prevents conformity-driven false cascades under conservative fallbacks.
-
Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
OKH-RAG represents knowledge as ordered hyperedges and retrieves coherent interaction sequences via a learned transition model, outperforming permutation-invariant RAG baselines on order-sensitive QA tasks.
-
LLMs Should Express Uncertainty Explicitly
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.
-
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
ReSeek adds self-correction via a JUDGE action and a dense instructive reward (correctness plus utility) to RL training of search agents, yielding higher success and faithfulness on a new contamination-resistant benchmark.
-
In-depth Analysis of Graph-based RAG in a Unified Framework
A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.
-
A-MEM: Agentic Memory for LLM Agents
A-MEM is a dynamic memory system for LLM agents that builds and refines an interconnected network of notes with agent-driven linking and evolution, showing performance gains over prior memory methods on six models.
-
ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.
-
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding, and QA tasks.
-
From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
A code-owned harness enforces source, routing, trace, hygiene, and recommendation contracts for enterprise LLM agents; prompt-only fails and bolt-on guardrails over-refuse.
-
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
SkillCenter provides 216,938 source-grounded skills across 24 domains via an automated LLM-based pipeline, with a downstream evaluation showing skills help agents only when the task exceeds the model's knowledge and retrieval surfaces the right skill.
-
PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement
PAPERCLAW is a multi-agent system for end-to-end autonomous research paper generation from literature to output, with human refinement and LLM-judge evaluation showing strong results.
-
Understanding and Debugging Failures in N-Gram-Based Generative Retrieval
Presents a taxonomy of generative retrieval failures, empirically identifies issues such as ambiguous docids and low diversity in n-gram methods, and introduces a web-based debugging tool.
-
TASR: Training-Free Adaptive Stopping for Iterative Retrieval
TASR provides a training-free predicate that stops iterative retrieval on repeated normalized answers plus calibrated logit margin above 0.25, retaining 94.8% of fixed-k=5 F1 at 62.6% of the calls across 32 configurations.
-
Strategic Decision Support for AI Agents
The paper introduces an optimization framework for AI agents to strategically seek support, proving a threshold policy on support value and providing an online algorithm to control missed-support error without distributional assumptions.
-
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
CICL scores and compresses context evidence for LLM agents via action-shift and outcome-uplift metrics, lifting hit@1 from 0.58 to 0.78 on 50 SWE-bench retrieval tasks.