{"slug":"question-answering","label":"Question Answering","item_count":4,"day_count":4,"source_count":3,"first_seen":"2026-10-23T09:50:37+00:00","last_updated":"2026-11-04T13:30:54+00:00","generated_at":"2026-11-06T00:13:28.162297+00:00","sources":["arxiv_agent_systems_research","arxiv_cs_cl","arxiv_llm_reliability"],"days":[{"date":"2026-10-23","items":[{"title":"Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images","url":"http://arxiv.org/abs/2610.32423v1","source":"arxiv_llm_reliability","type":"paper","summary_1line":"Recent advances in Vision-Language Models (VLMs) have significantly improved Visual Question Answering (VQA) performance, yet their reasoning over structured content such as tables remains inconsistent, often plagued...","why_it_matters":"Matches feed focus: evaluation.","sid":"1846766ba5a6742d","published":"2026-10-23T09:50:37+00:00","editor_note":"Iterative self-evaluation for table VQA over document images."}]},{"date":"2026-10-26","items":[{"title":"Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations","url":"http://arxiv.org/abs/2610.35598v1","source":"arxiv_llm_reliability","type":"paper","summary_1line":"Knowledge graphs (KGs) provide reliable external knowledge for multi-hop factual reasoning with large language models (LLMs), yet most KGs in real-world domains such as finance and industry lack question--answer (QA)...","why_it_matters":"Matches feed focus: agent, eval.","sid":"26fc92a7573c4011","published":"2026-10-26T15:23:04+00:00","editor_note":"Knowledge-graph reasoning that evolves without QA annotations."}]},{"date":"2026-10-27","items":[{"title":"DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering","url":"http://arxiv.org/abs/2610.36759v1","source":"arxiv_agent_systems_research","type":"paper","summary_1line":"Multilingual multi-hop document question answering (MMHop-DocQA) requires locating and integrating evidence across complex layouts, document pages, and diverse languages. Existing approaches include single-pass proces...","why_it_matters":"Matches feed focus: agentic, eval.","sid":"334116357c766a21","published":"2026-10-27T07:14:59+00:00","editor_note":"Agentic skills applied to multilingual multi-hop document QA."}]},{"date":"2026-11-04","items":[{"title":"LibriSpeech-Real-QA: A Benchmark for Streaming Question Answering","url":"http://arxiv.org/abs/2611.06496v1","source":"arxiv_cs_cl","type":"paper","summary_1line":"Most speech large language models (SLMs) still process speech in an offline manner. They only start responding after they receive the complete speech segment. However, many real-world applications require streaming sp...","why_it_matters":"Matches feed focus: evaluation.","sid":"81f93605a5cf2115","published":"2026-11-04T13:30:54+00:00","editor_note":"Adds a benchmark for streaming speech QA, a new modality for the thread."}]}],"editorial":{"tldr":"Late-October arXiv papers attacked question answering where plain LLM calls fall short: tables in document images and knowledge graphs without QA annotations. A multilingual multi-hop document QA paper then added agentic skills.","stale":false,"whats_new":"LibriSpeech-Real-QA (Nov 4) is a benchmark for streaming question answering, where speech LLMs must respond before the full audio segment has arrived.","why_it_matters":"These are research papers, not products, but they show QA moving toward iterative self-checking, agentic skills and streaming input, which change latency and eval design for pipelines.","take_for_builders":"Treat these as preprints: if you run document or speech QA, note the benchmarks they introduce and wait for independent reproductions before changing a pipeline.","beats":[{"kicker":"DOCUMENTS & GRAPHS","tone":"launch","headline":"Self-evaluation and self-evolution for table and knowledge-graph QA","sids":["1846766ba5a6742d","26fc92a7573c4011"]},{"kicker":"AGENTIC","tone":"rising","headline":"DocSkill brings skill-integrated agents to multilingual multi-hop document QA","sids":["334116357c766a21"]},{"kicker":"NOW","tone":"now","headline":"LibriSpeech-Real-QA benchmarks streaming question answering for speech LLMs","sids":["81f93605a5cf2115"]}],"open_questions":["Do any of these methods report results that hold up outside their own benchmarks?","Will speech LLMs show measurable accuracy loss when answering before the full audio arrives?"],"generated_at":"2026-11-06T00:12:51+00:00"}}