TechniqueRLHF / Alignment8 recent entries27 Aug 2026FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk ReviewarXiv:2608.25325v1 Announce Type: cross Abstract: Deploying large language models for professional financial review requires more than measuring general financial competence: models must perform the s→28 Aug 2026From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and SegmentationarXiv:2608.26856v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in Medical Visual Question Answering (Med-VQA), their relia
TechniqueRAG8 recent entries28 Aug 2026From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and SegmentationarXiv:2608.26856v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in Medical Visual Question Answering (Med-VQA), their relia→1 Sept 2026PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented GenerationarXiv:2608.29753v1 Announce Type: new Abstract: Multi-hop question answering in retrieval-augmented gener?ation (RAG) often benefits from retrieving beyond the few candidates that will finally be read→1 Sept 2026Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQAarXiv:2608.28635v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their r→10 Sept 2026Vague2Detect: Handling Ambiguous Prompts in Knowledge-Based Open-World DetectionarXiv:2609.09949v1 Announce Type: cross Abstract: Real-world detectors must often interpret functional or ambiguous prompts, yet conventional models such as YOLO remain restricted to fixed class lists→10 Sept 2026OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst queryingarXiv:2609.08869v1 Announce Type: cross Abstract: Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-mo→28 Sept 2026ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement LearningarXiv:2609.30906v1 Announce Type: new Abstract: Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promisin→7 Oct 2026SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data SynthesisarXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-qu→12 Oct 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAarXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-
TechniqueAgents8 recent entries17 Sept 2026XingChen-AGI/Xing4.0-29B-A4B MoEI find another new model at HF: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B 'Xing4.0-29B-A4B is a next-generation large language model in the Xing series (formerly TeleChat), developed by Chin→23 Sept 2026ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in ChemistryarXiv:2511.17909v2 Announce Type: replace Abstract: Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often rel→28 Sept 2026ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement LearningarXiv:2609.30906v1 Announce Type: new Abstract: Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promisin→29 Sept 2026Inductive Feedback for Mixed-Policy DistillationarXiv:2609.35390v1 Announce Type: new Abstract: Verbal feedback can identify errors and prescribe corrections, providing rich supervision for language-model post-training even when reliable programmat→2 Oct 2026KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable RewardsarXiv:2610.02206v1 Announce Type: cross Abstract: LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existi→7 Oct 2026SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data SynthesisarXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-qu→7 Oct 2026Running an open-source agent platform with no third party in the chain: what each piece needs (Ollama/vLLM, local embeddings, local OCR)Disclosure first: I work at Vstorm and I build AgenticOS, an open-source (Apache-2.0), self-hosted platform for building AI agents in a browser. This post was drafted with an LLM's help and edited by →12 Oct 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAarXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-
TechniqueFine-tuning8 recent entries14 Aug 2026HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQAarXiv:2608.13004v1 Announce Type: new Abstract: Knowledge-base question answering (KBQA) systems rely on effective retrieval and reasoning mechanisms to generate accurate answers from external knowled→18 Aug 2026mR^2AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQAarXiv:2411.15041v2 Announce Type: replace Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and E→24 Aug 2026Enhancing LLMs in Predictive Political QA with Semi-Structured DataarXiv:2608.21218v1 Announce Type: new Abstract: Predictive political question answering (QA), such as predicting how a political actor will vote, goes beyond factual lookup. External political resourc→27 Aug 2026A Layered Security Framework Against Prompt Injection in RAG-Based ChatbotsarXiv:2606.19660v2 Announce Type: replace-cross Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applicatio→10 Sept 2026Vague2Detect: Handling Ambiguous Prompts in Knowledge-Based Open-World DetectionarXiv:2609.09949v1 Announce Type: cross Abstract: Real-world detectors must often interpret functional or ambiguous prompts, yet conventional models such as YOLO remain restricted to fixed class lists→17 Sept 2026XingChen-AGI/Xing4.0-29B-A4B MoEI find another new model at HF: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B 'Xing4.0-29B-A4B is a next-generation large language model in the Xing series (formerly TeleChat), developed by Chin→2 Oct 2026KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable RewardsarXiv:2610.02206v1 Announce Type: cross Abstract: LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existi→7 Oct 2026SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data SynthesisarXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-qu
TechniqueMultimodal8 recent entries1 Sept 2026Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQAarXiv:2608.28635v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their r→11 Sept 2026Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity LinkingarXiv:2609.10745v1 Announce Type: new Abstract: Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work m→23 Sept 2026ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in ChemistryarXiv:2511.17909v2 Announce Type: replace Abstract: Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often rel→1 Oct 2026When Can Text Replace Vision? Structural Bottlenecks in Diagram ReasoningarXiv:2609.39142v1 Announce Type: new Abstract: Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the→1 Oct 2026TED:Text-Axis Evidence Decomposition for Prompted Anomaly LocalizationarXiv:2609.39033v1 Announce Type: cross Abstract: CLIP is a powerful vision-language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt i→5 Oct 2026Evaluating VQA in Vision Language Models using Cooperative PrinciplesarXiv:2610.02878v1 Announce Type: new Abstract: We evaluate the performance of Vision Language Models in Visual Question Answering (VQA) when questions violate Grice's maxims. To do this, we use VLMs →7 Oct 2026SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data SynthesisarXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-qu→12 Oct 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAarXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-
TechniqueSafety8 recent entries31 Jul 2026BridgeAlign: Bridging Preference Alignment for Humanities and Social SciencesarXiv:2607.27366v1 Announce Type: new Abstract: While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanit→3 Aug 2026TELLER: Dual-Path Iterative Preference Optimization for Table Entity LinkingarXiv:2607.28680v1 Announce Type: new Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on→5 Aug 2026Measurement Without Validity: The Compounding Reliability Problem in Agentic AI EvaluationarXiv:2608.00794v2 Announce Type: replace Abstract: Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims.→25 Aug 2026Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question AnsweringarXiv:2608.21450v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, ex→27 Aug 2026A Layered Security Framework Against Prompt Injection in RAG-Based ChatbotsarXiv:2606.19660v2 Announce Type: replace-cross Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applicatio→2 Sept 2026A Unified Mechanistic Analysis of Knowledge- and Safety-Based RefusalsarXiv:2609.00760v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safe→10 Sept 2026PiMRef: Deducing Ever-evolving Spear-phishing Emails with Knowledge Base InvariantsarXiv:2507.15393v2 Announce Type: replace-cross Abstract: Phishing email is a critical step in the cybercrime kill chain due to the high reachability of victims' email accounts and the low cost of lau→29 Sept 2026Inductive Feedback for Mixed-Policy DistillationarXiv:2609.35390v1 Announce Type: new Abstract: Verbal feedback can identify errors and prescribe corrections, providing rich supervision for language-model post-training even when reliable programmat