evidence retrieval

The papers

Most central to this idea first, not most recent.

• Academiccs.SE

  Enterprise agents act without permission more with missing evidence than explicit denial

  Enterprise agents correctly obey explicit permissions but fail to stop when supporting evidence is missing.

  Independent Researcher, University of Southern California · Nov 2026

• Top Universitycs.AI

  Linking memory back to raw data helps AI agents avoid repeating bad lessons

  Evidence-linked memory, storing lessons with their source trajectories, reduces failures caused by incorrect or misapplied lessons in LLM agents.

  KAIST, DeepAuto.ai · Nov 2026

• Big Techcs.CL

  Search results order and dead-end histories bias AI agents' final answers

  Final answers of search-equipped LLM agents are more sensitive to initial evidence order than when all evidence is supplied, and dead-end work reduces strategy switching.

  Amazon Web Services · Nov 2026

• Top Universitycs.AI

  Backtesting method lets AI agents forecast past events for instant feedback

  FABench reveals retrieval helps agents match market forecasts, yet evidence weighing remains a critical failing.

  Raven Labs, Zhejiang University · Nov 2026

• Big Techcs.IR

  AI agents find better evidence when search considers their original question

  ACARe uses agent context to rerank documents, improving retrieval and answer accuracy in multi-step search.

  University of Waterloo, NVIDIA · Oct 2026

• Top Universitycs.CL

  RAG's retrieval, not reading, is the bottleneck for long-context question answering

  Similarity-based RAG fails long-context multi-fact QA because retrieval cannot surface all needed chunks and chunking loses document metadata, not because reading is inadequate.

  MBZUAI, Inception42 · Oct 2026

• Chinese Techcs.CV

  OACap turns video captioning into active, tool-guided observation

  OACap improves detailed video captions by using missing or unsupported claims to guide targeted observations, then revising descriptions against the resulting evidence.

  Ant Group, Zhejiang University · Oct 2026

• Chinese Techcs.CV

  Agentic image checks test depicted facts, not AI provenance

  EviScene is an agent that assesses image factuality by iteratively refining questions and gathering external evidence.

  Jilin University, Institute of Automation, Chinese Academy of Sciences · Oct 2026

• Big Techcs.IR

  Co-Adaptive Routing and Retrieval Learns Query Rules Without Supervision

  CoRE jointly learns reasoning rule routing and constrained retrieval for structured knowledge without query-rule supervision.

  University of Georgia, Michigan State University · Oct 2026

• Chinese Techcs.AI

  Neos turns visual evidence into better follow-up search decisions

  Neos learns to interleave search and visual reasoning, achieving leading performance on multimodal deep search benchmarks.

  Fudan University, Accio Team, Alibaba Group · Oct 2026

• Big Techcs.CR

  Multi-agent adversarial review boosts LLM-based SOC alert triage accuracy

  Structuring LLM agent evidence retrieval and adversarial review substantially improves SOC alert triage, raising F1 from at most 0.744 to 0.958.

  Virginia Tech, Google · Oct 2026

• Big Techcs.CL

  One LLM mechanism handles both retrieval and long-context evidence selection

  A single frozen LLM with fewer than 500K trainable parameters handles both corpus retrieval and long-context evidence selection.

  NVIDIA, Technion · Oct 2026

• Chinese Techcs.CV

  Adaptive visual memory cuts multimodal reasoning costs without losing accuracy

  Adaptive selection of fine-grained visual tokens during decoding improves multimodal reasoning accuracy and efficiency compared with one-shot compression.

  City University of Hong Kong, Zhejiang University · Oct 2026

• Chinese Techcs.CL

  Temporal structure improves long-term memory retrieval for multi-party LLM agents

  Temporal structure, used for evidence recovery and state-transition reconstruction, improves long-term multi-party conversational memory.

  Beihang University, Alibaba Group · Oct 2026

• Top University

  Retrieval-based checks miss many factual errors in open-ended medical answers

  Retrieval-based factuality evaluation of long-form medical answers fails because scaling retrievers, verifiers, reasoning, and medical tuning does not fix fundamental error modes.

  Center for Language and Speech Processing, Johns Hopkins University · Sept 2026

• Chinese Techcs.CV

  Clinical agents learn to gather evidence across longitudinal MRI records

  CASE agents achieve over 16% and 10% relative improvements in answer accuracy over GPT-5.4 and Claude Opus 4.8 on longitudinal medical reasoning.

  Durham University, DAMO Academy, Alibaba Group · Oct 2026

• Big Techcs.PL

  Agentic copilot accelerates ML accelerator co-design by grounding insights in fresh simulation data

  Coco automates simulation experiments and data analysis to accelerate hardware-software co-design for ML accelerators.

  Google, Google DeepMind · Oct 2026

• Big Techcs.CV

  Image forensics protocol sorts AI edits into retouching, tampering, and full synthesis

  A dual-channel protocol distinguishes retouched, tampered, and synthetic images beyond binary real/fake labels.

  Google, University of British Columbia · Nov 2026

• Academiccs.MA

  Adaptive interaction routing improves multimodal AI debate accuracy while cutting token use

  AIM boosts multimodal debate accuracy by adaptively choosing text, graph, or region-based interaction per query.

  Virginia Tech, Inha University · Nov 2026

• Top Universitycs.CV

  Agent workflows help AI combine several reference images, but gains vary

  LongBanana is a 90-task expert-verified benchmark that scores long-context multi-reference image synthesis by checking atomic, graph-grounded constraints rather than a single holistic image-quality score.

  South China Normal University, University of British Columbia · Nov 2026

• Chinese Techcs.CL

  RL-trained agents search multilingual corpora directly, beating retrieval methods

  MARS uses reinforcement learning to train multilingual search agents that directly query raw corpora via shell commands, improving evidence acquisition and reducing redundancy.

  Beijing Jiaotong University, Tencent Inc. · Nov 2026

• Independentcs.AI

  Simple retrieval rivals complex memory systems on conversation benchmarks

  Naive RAG with dense retrieval and reranking over raw history outperforms complex agentic memory systems on most long-term conversation benchmarks.

  Oct 2026

• Chinese Techcs.AI

  AI agents can improve by tracing how shared evidence changes answers

  SPLICE locates information gaps in multi-agent workflows, adds one edge to deliver missing evidence, and adopts only when process changes confirm, raising Web tool use by 8.0%.

  University of Science and Technology of China, Qwen Business Unit of Alibaba · Oct 2026

• Chinese Techcs.LG

  Separating search and answer credit improves accuracy and evidence grounding

  Separating search and answer credit improves both exact-match accuracy and evidence grounding in reinforcement-trained multi-turn search agents.

  South China University of Technology, FiT, Tencent · Oct 2026

• Big Techcs.LG

  Training LLM forecasters across dates improves search and probability estimates

  Training an LLM forecaster to search evidence and report probabilities at multiple pre-resolution dates improves forecast accuracy and calibration.

  Amazon Data & Models, Georgia Institute of Technology · Oct 2026

• Big Techcs.CV

  Compact reusable memory improves question answering over hour-long videos

  Video-EMem encodes long videos once into compact time-anchored text and sparse images, then retrieves evidence per query, improving accuracy and cutting latency.

  Zhejiang University, Microsoft Research Asia · Oct 2026

• AI Startupcs.CV

  Frontier text-to-image models score as low as 23.9 on hardest benchmark

  The best text-to-image model scores only 23.9 out of 100 on the GenOlympiad benchmark of hard prompts.

  Australian National University, Canva · Oct 2026

• Chinese Techcs.CV

  Evidence-grounded benchmark forces models to show their reasoning for audio-visual tasks

  EvaOmni is an evidence-grounded benchmark that requires audio-visual reasoning models to return supporting evidence intervals, scored for coverage and localization.

  Shanghai Jiao Tong University, Fudan University · Oct 2026

• Big Techcs.CL

  Translation agents learn to retrieve evidence only when it improves results

  LLM translation improves by learning when and what to retrieve instead of always retrieving.

  The University of Texas at Austin, Amazon · Oct 2026

• Top Universitycs.AI

  Memory Tests Must Separate What Agents Keep From What They Retrieve

  Memory evaluations confound retention with retrieval; most apparent query-awareness gains are actually history access, so benchmarks should hold access fixed and report both separately.

  Stanford University · Oct 2026

• Chinese Techcs.CV

  Video agent answers questions about one video in a single shared reasoning pass

  Coordinating multiple questions about one video in a single shared agent trajectory improves accuracy and cuts reasoning rounds and frames.

  University of Science and Technology of China, Tencent · Oct 2026

• Chinese Techcs.CV

  Preserving Retrieved Images Improves Long-Term Multimodal Agent Memory

  For multimodal memory agents, how retrieved evidence is presented (delivery) affects accuracy more than retrieval perfection.

  Huawei Technologies Ltd., Huawei Pisa Research Center · Sept 2026

• Academiccs.CL

  Dual-system agent couples fast evidence checks with deliberative planning for efficient research

  JevGPT couples fast evidence processing with deliberative planning to achieve leading performance, lower cost, and faster completion.

  King Abdullah University of Science and Technology · Oct 2026

• Academiccs.CR

  Security agents lose evidence support when available telemetry changes

  When telemetry changes, LLM agents lose citation support for 35.5% of previously covered attack actions even though the actions remain recoverable.

  Zhongguancun Laboratory · Oct 2026

• Chinese Techcs.CV

  Parallel tile inspection helps models find details in large images

  Visual Parallel Search with parallel tile inspection and adaptive zoom improves high-resolution VQA accuracy.

  The University of Hong Kong, Huawei Research · Oct 2026

• Academiccs.AI

  Bilevel optimization bridges the retriever-policy credit gap in agentic RL

  Training retrieval before policy optimization, then co-adapting both with bilevel optimization, improves retrieval-augmented LLM agents’ question-answering accuracy while reducing retriever-update memory.

  Cornell University, Institute of Science Tokyo · Oct 2026

• Big Techcs.CV

  Active audio-visual tool use improves reasoning across long recordings

  OmniSeek improves long-context audio-visual reasoning by letting models iteratively retrieve and combine targeted raw audio and video evidence.

  Adobe Research, University of California Davis · Oct 2026

• Academic

  Scoping Agent Memory Prevents Unrelated Tasks From Disrupting Each Other

  Family-scoped retrieval prevents cross-family interference and supports repeated adaptation in persistent agent memory.

  Independent, Northwestern University · Sept 2026

• Industrycs.LGcode

  Training Forecasters to Search Improves Calibration and Reduces Tool Use

  Training language models to gather their own evidence during reinforcement learning improves forecasting and beats frontier models at lower cost.

  Future Principle · Oct 2026

• Chinese Techcs.AI

  Web agents struggle with multilingual, multimodal evidence hunts across the web

  HyperBrowseComp is a 423 question benchmark across 13 languages and multiple modalities that challenges web browsing agents.

  Mohamed bin Zayed University of Artificial Intelligence, Mila – Quebec Artificial Intelligence Institute · Oct 2026

• Big Techcs.CL

  Entity maps help search agents connect evidence across documents

  Organizing a document corpus into entity pages linked to source documents improves agentic search evidence discovery and answer quality while reducing token use.

  KAIST, Microsoft · Sept 2026

• Chinese Techcs.LG

  Execution graph helps off-the-shelf teachers supervise student agents better

  Graph-conditioned retrieval of teacher execution histories improves on-policy distillation for compact language agents in multi-turn tasks.

  Yuanbao Team, Tencent, Tsinghua University · Sept 2026

• Chinese Techcs.CV

  Evolved agent harnesses cut long-video analysis costs while improving accuracy

  VidHarness automatically evolves video agent harnesses, achieving state-of-the-art long video QA with fewer frames.

  Baidu, Inc. · Oct 2026

• Big Techcs.SE

  New benchmark tests AI's ability to spot invalid code reviews

  AI agents can judge if a code review comment is technically correct by gathering repository evidence, outperforming general LLMs.

  University College London, Amazon · Sept 2026

• Big Techcs.CL

  Agentic document QA pays off mainly with stronger vision-language models

  For long-document VLM QA, retrieving images beats retrieving text, agentic tools only pay off with large readers, and per-question pipeline selection wins by roughly 13 points.

  Amazon.com · Sept 2026

• Big Techcs.AI

  Retrieving existing agent skills improves optimization across different execution harnesses

  RASO leverages an external skill corpus through initialization and update, adapting retrieved skills across harnesses, and outperforms retrieval-free baselines on four benchmarks.

  Korea University, KAIST · Sept 2026

• Chinese Techcs.CL

  Selecting evidence before summarizing improves long-context reasoning efficiency

  Highlighting and summarizing relevant evidence before answering improves long-context reasoning and allows more compact output.

  Peking University, Baidu Inc. · Sept 2026

• Independentcs.AI

  DSA orchestrates evidence-aware stock research across six regional markets

  DSA is an evidence-aware orchestration framework for multi-market stock research with LLM agents.

  Aug 2026

• Independentcs.AI

  Most AI agents score under 66% on workplace questions spanning chat and code

  Most AI agents score below 66% on collaborative project tasks requiring joint reasoning over conversations, code, and documents.

  Nov 2026

• Top Universitycs.CL

  Proactive assistance requires choosing the right moment, not just the right words

  ProPerAgent improves proactive assistance by retrieving long-term personal memories, gating interruptions, and training against premature or repeated responses.

  Michigan State University, Meta Reality Labs · Oct 2026

• Top Universitycs.AI

  New benchmark tests AI judges on long computer-use tasks by swapping instructions

  A benchmark of 1,373 paired computer-use tasks shows current judges, best GPT-5.5 at 80.9% balanced accuracy, often miss subtle instruction violations.

  ServiceNow Research, McGill University · Oct 2026

• Chinese Techcs.AI

  Incorrect peer messages can override an agent’s evidence-backed answer

  In multi-agent LLM systems, incorrect upstream messages override correct downstream answers in up to 32% of cases; 94% of harmful cases copy the upstream's wrong answer.

  University of Science and Technology of China, Qwen Business Unit of Alibaba · Sept 2026

• Top Universitycs.AI

  Benchmark reveals AI systems struggle to retrieve papers that inspire new research

  Current retrieval systems recover at most 48% of catalyst papers that authors credit.

  Stanford University, Seoul National University · Oct 2026

• Big Techcs.CL

  Execution-verified feedback improves LLM harness optimization for SQL, Cypher, and Python generation

  HERO improves pass@1 by 7.6 points offline and an additional 2.0 points via test-time refinement on text-to-code benchmarks.

  University of Washington, Microsoft Research · Oct 2026

• Chinese Techcs.AI

  Diagnosis-first framework boosts solver performance across numerical domains

  ADSD links numerical diagnosis to reusable solver skill discovery, improving solver accuracy, robustness, and efficiency across four numerical domains.

  University of California, Berkeley, Alibaba Group · Oct 2026

• Top Universitycs.CV

  Text queries retrieve SAE features for steering diffusion transformers

  D-Scope retrieves sparse autoencoder decoder directions for diffusion transformers by matching text queries to visual centroids of activating patches, enabling interpretable generation steering.

  Pivotal Research, Mohamed bin Zayed University of Artificial Intelligence · Oct 2026

• Big Techcs.AI

  Replayable news timelines test how LLM agents update forecasts

  Replayable historical forecasting environments let LLM agents research dated news, lowering Brier scores across 12 models, though all still trail market forecasts.

  Georgia Institute of Technology, Amazon · Sept 2026

• Big Techcs.AIcode

  Entity-structured indexes help agents retrieve precise long-term memories

  Entity-structured indexing with episode provenance improves long-term agent memory retrieval and answer accuracy over summary-based systems.

  University of Illinois Urbana-Champaign, Amazon · Sept 2026

• Big Techcs.AI

  Speaker-indexed memory cuts token costs while preserving answer accuracy

  Stashbird reduces memory token usage by up to 76x while achieving competitive question answering accuracy across long-term conversation benchmarks.

  Microsoft · Sept 2026

• Chinese Techcs.AIcode

  C3M preserves multimodal evidence across sessions within fixed memory budgets

  C3M maintains a bounded active index over persistent text-image evidence with relation-aware updates and budgeted routing, improving accuracy on cross-session long-horizon tasks.

  Huzhou Normal University, Alibaba Group · Sept 2026

• Academiccs.CLcode

  AI chatbots fail long tasks due to competing content, not length

  In language-model retrieval, competing facts, not context length alone, drive failures, and attention remaining on the evidence predicts when they occur.

  University of California San Diego · Nov 2026

• Chinese Techcs.CV

  AI models can answer plot questions while struggling to identify speakers

  Multimodal models fail to bind spoken dialogue to the correct speaker, and visual input can actively degrade dialogue-centric narrative reasoning.

  ShanghaiTech University, Institute of Automation, Chinese Academy of Sciences · Nov 2026

• Chinese Techcs.SE

  Coding agents struggle to connect code changes with repository behavior

  SWE-Time shows coding agents still struggle to reason reliably about how code changes explain past bugs and shape future behavior.

  Nankai University, Baidu, Inc. · Nov 2026

• Academiccs.CL

  Visual encoding lets language models answer questions with 16 tokens instead of thousands

  OpticalRAG compresses retrieved documents into 16 visual tokens using rendered page images, improving accuracy while drastically reducing token usage.

  Renmin University of China, ComindX · Nov 2026

• Academiccs.IR

  AI health overviews cite fewer top sources and often lack evidence

  Google’s health AI Overviews often cite weaker sources, make unsupported or uncited claims, and provide incomplete or inaccurate answers.

  Northwestern University · Oct 2026

• Independentcs.AI

  AI agents can explore alternative plans without copying shared environments

  Agentic World Modeling enables test-time scaling by simulating actions through read-only environment queries.

  Nov 2026

• Big Techcs.AI

  AI agents’ false completion claims are caught more often with follow-up checks

  Treating verification as active exploration of interfaces and code beats passive judging for computer-using agents.

  Google, The University of Hong Kong · Oct 2026

• Industrycs.AI

  AI agents can reconstruct five years of tax records in minutes

  Below frontier models, the harness, not the model, determines how well agents solve messy real-world knowledge work; on frontier models the task collapses.

  G.S. s.r.o, PwC Austria · Oct 2026

• Chinese Techcs.AI

  AI agents that satisfy more search constraints recommend fewer places

  An agentic local search benchmark reveals a core trade-off between task coverage and reliable constraint satisfaction.

  Alibaba Group · Oct 2026

• Chinese Techcs.AI

  Teaching data agents to use charts inside their reasoning loop improves analysis

  Data agents that choose charts as intermediate evidence within their reasoning loop improve analytical accuracy, and experience distillation teaches them when to draw and read charts.

  Tencent, Renmin University of China · Oct 2026

• Chinese Techcs.CV

  AI models answer long-video questions over 50% better with memory tools

  A memory-centric harness with specialized tools improves foundation model performance on long-horizon spatiotemporal tasks by over 50%.

  Nanyang Technological University, Token Foundry, Alibaba · Oct 2026

• Big Techcs.CL

  Shared message search lets LLM agent groups scale without flooding readers

  Multi-agent LLM systems scale better when agents coordinate through a shared datastore with bounded reads and citation-based ranking.

  FAIR at Meta, Harvard · Oct 2026

• Top Universitycs.CV

  VLMs mostly err by ignoring visual evidence they possess

  Most vision-language model errors are due to failing to use visual information that is already encoded.

  Technion · Oct 2026

• Chinese Techcs.CL

  Adaptive training harness keeps rubric rewards useful as policies improve

  HarnessRL co-evolves task sampling, rollout guidance, and rubric criteria during RL training, beating baselines by 2.8-3.1 points on open-ended tasks.

  Alibaba Token Hub, Alibaba Group, Université de Montréal · Oct 2026

• Chinese Techcs.CV

  Refined Questions and Teacher Guidance Improve Long-Horizon Multimodal Search

  MMSearch-OPD improves long-horizon multimodal search agents by combining data refinement with joint reinforcement learning and on-policy distillation.

  Peking University, HKUST(GZ) · Oct 2026

• Big Techcs.AI

  Agentic verification improves outputs on long-horizon workspace tasks

  VeriHarness uses the generator's own model as an agentic verifier to improve selection and revision of long-horizon task artifacts.

  Google Cloud AI Research, University of Cambridge · Oct 2026

• Top University

  Shared agent memories confuse repeated claims with independent evidence

  Gating on declared source type reduces false adoption in shared agent memory, but no policy consistently rejects false claims.

  University of Southern Queensland, University of New South Wales · Sept 2026

• Big Techcs.CL

  Confidence-guided complementary evidence pool improves multimodal retrieval-augmented generation

  CLIMB selects complementary evidence and uses confidence scores to decide when to update answers, improving multimodal RAG without retraining.

  Rutgers University, Google · Oct 2026

• Big Techcs.CV

  Grounding long-video memories in visual identity lets QA systems track objects across days

  Grounded Entity Biographies link visually identified objects across video clips to answer questions about long recordings.

  University of Illinois Urbana-Champaign, Amazon.com, Inc. · Sept 2026

• Big Techcs.CL

  Distributed grounding preserves reasoning across million-token language model contexts

  DISCO separates parallel, sharded evidence grounding from centralized reasoning, preserving long-context accuracy while cutting inference cost versus monolithic full-context models.

  National University of Singapore, Adobe Research · Sept 2026

• Independentcs.AI

  Query-aware evidence forests improve long-term memory for multimodal agents

  GraphMemix organizes memory into query-aware evidence forests, improving accuracy and reducing lifecycle cost for multimodal agents.

  Aug 2026

• Chinese Techcs.CV

  Visual puzzle solvers improve by building explicit problem states

  Explicit, revisable problem states, built from visual inspection and executed by generated programs, improve accuracy on visual reasoning benchmarks.

  SenseTime Research, Tetras.AI · Nov 2026

• Top Universitycs.CV

  AI models struggle to report video tampering their internal features reveal

  Separate audio and visual temporal readouts on frozen AV-LLM features outperform zero-shot prompting for manipulation localization.

  Tsinghua University, Peking University · Oct 2026

• Big Techcs.CL

  Visual agents improve when tool evidence persists across reasoning steps

  OpenVLHarness improves visual-agent reasoning by combining normalized tool interfaces, model-readable evidence, persistent multimodal artifacts, and code execution over stored results.

  University of California, Los Angeles, Apple · Oct 2026

• Chinese Techcs.CV

  Search agents that locate, verify and crop references improve image generation for recent events.

  A locate-corroborate-isolate search agent retrieves better references for newly introduced, easily confused entities and improves downstream image generation quality.

  Renmin University of China, Tencent · Oct 2026

• Top Universitycs.AI

  Sparse replay memory extends linear attention to million-token contexts

  NoteBank, a training-free episodic memory, improves long-context retrieval in linear attention from 1.7% to 70.3% at one million tokens.

  King Abdullah University of Science and Technology (KAUST) · Oct 2026

• Chinese Techcs.CV

  Benchmark and agent for verifying images against real-world facts

  Persistent, state-guided verification detects image-world factual conflicts better than direct or retrieval-augmented judgment on evaluated 8B vision-language models.

  Ant Group, Tsinghua University · Oct 2026

• Chinese Techcs.LG

  Evidence annotations improve step-level credit for deep search agents

  Evidence-guided step-level process rewards derived from annotated evidence claims improve credit assignment and outperform standard GRPO on deep search benchmarks.

  Renmin University of China, Key Laboratory of Data Engineering and Knowledge Engineering, MOE · Oct 2026

• Chinese Techcs.AI

  LLM authorization gates frequently block benign actions when safety alignment overrides explicit user permission

  Authorization gates using LLMs for coding agents often block explicitly authorized actions due to over-reliance on internal safety alignment, and retrospective environment signals improve accuracy.

  Huawei Technologies Ltd., Sun Yat-sen University · Oct 2026

• Big Techcs.AI

  Program-graph evidence and blinded LLM surrogates detect code equivalence gaps

  Graph-grounded, blinded surrogate execution finds behavioral differences that benchmark labels and passing unit tests miss while abstaining when evidence is incomplete.

  AWS AI Labs · Oct 2026

• Chinese Techcs.AI

  AI agents complete more phone tasks by remembering smaller goals

  Storing GUI agent experience as subgoal-level memory graph improves success rate by 11.11% on SPA-Bench.

  Huawei Noah's Ark Lab · Oct 2026

• Top Universitycs.CLcode

  Runtime research preserves details that prebuilt agent memories can lose

  Just-In-Time Agent Memory constructs query-relevant context at runtime, outperforming Ahead-of-Time systems and prior trained memory.

  Beijing Academy of Artificial Intelligence, Peking University · Sept 2026

• Academic

  Web agents struggle to turn search results into usable artifacts

  Frontier computer-use agents fully complete fewer than 3% of long-horizon web tasks requiring synthesis and artifact creation, and visual/spatial failures often make partial artifacts unusable.

  University of Utah · Sept 2026

• Big Techcs.AI

  Filtering pages before they reach AI search blocks over 80% of hidden attacks

  SearchInject reduces exposure to injected pages in tested search systems by 83.2–83.7% with little change to clean-result ranking quality.

  Google LLC, Harvard University · Nov 2026

• Chinese Techcs.CL

  Workspace-grounded synthesis scales verifiable training for long-horizon work agents

  WorkForge builds verifiable work-agent environments from real-world files by anchoring tasks and verifiers in observable workspace facts, improving agent performance across benchmarks.

  Tencent, Fudan University · Oct 2026

• Chinese Techcs.SE

  Diagnostic tools speed agentic root cause analysis, but accuracy varies

  Higher-level diagnostic tools reduce localization accuracy but improve failure type identification and speed in agentic RCA.

  Nankai University, Huawei Technologies Co., Ltd. · Oct 2026

• Chinese Techcs.CL

  Building LLM memory at test time beats offline memory systems for long histories

  Deferring memory construction to inference and building it progressively during reasoning improves long-context question answering with lower overhead.

  Northeastern University, Tsinghua University · Oct 2026

• Big Techcs.CV

  Training-free visual memory framework compresses video tokens while preserving event coherence

  KeyRec uses a bounded visual memory with a recent cache and event bank to compress video for VLMs, using 10% of the token budget while improving accuracy.

  University of Virginia, Google · Oct 2026

• Top Universitycs.CL

  Self-programmed memory adapts retrieval depth to each agent query

  MemCodex improves task success by 10.1% with 3.4x fewer tokens and 2.1x faster inference.

  Université de Montréal, Mila – Quebec AI Institute · Oct 2026

• Chinese Techcs.CLcode

  Tree-tracing reinforcement learning improves reasoning across long dialogue histories

  StateTree uses a tree-structured RL task to improve long-term dialogue reasoning, outperforming baselines on LongMemEval.

  Zhejiang University, Taobao & Tmall Group of Alibaba · Oct 2026

• Chinese Techcs.AI

  Research agents can reuse experience to avoid unnecessary experiments

  Experimental Experience Modeling improves autonomous research by reusing accumulated experimental experience and acquiring new experience only when needed.

  State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · Oct 2026

• Independentcs.SE

  Enterprise agents struggle when facts are hidden across business systems

  Enterprise agents struggle on benchmark questions whose answers depend on facts implied across data sources, not explicitly stated.

  Sept 2026

• Top Universitycs.CL

  LLM agents struggle to infer wellbeing from long-term wearable data

  LLM-based agents for longitudinal mental health sensing rarely outperform a simple mean baseline, requiring stronger backbones or compact features.

  Dartmouth College, University of Cambridge · Aug 2026

• Chinese Techcs.SE

  Self-evolving harness turns general AI agents into stronger RCA specialists

  OpsHarness, a self-evolving harness, improves root cause analysis accuracy by 63.4% over a bare general agent.

  The Chinese University of Hong Kong, Individual Researcher · Aug 2026

• Top Universitycs.AI

  Structured experiment orchestration helps agents improve models without benchmark hacking

  RSI-Master uses an Experiment OS and reviewer-guided research DAG to stop hacking and strategy lock-in, improving autonomous post-training model development.

  Shanghai Jiao Tong University, Carnegie Mellon University · Sept 2026

• Big Techcs.CV

  New benchmark tests if AI can track objects after they vanish from view

  Vision-language models struggle to reason about objects moved out of sight, reaching only 42.2% on a new 9,000-question egocentric video benchmark.

  ETH Zurich, Microsoft Spatial AI Lab · Oct 2026

• Chinese Techcs.CL

  Rubric-based process rewards improve deep research agents’ evidence gathering

  Rubric-grounded process credit, which tracks accumulated support per rubric, improves deep research agent performance and enables an 8B model to match proprietary systems.

  University of Chinese Academy of Sciences, State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) · Sept 2026