NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
103 results for “keyword:"search agents"” in ICLR 2027. 26 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development▲9.2k2.67
[PDF]FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability▼5.8k2.33
[PDF]Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts▲11.00
[PDF]RACE: Learning Multimodal Search through Referential Abstraction and Compositional Evidence▲3.0k2.33
[PDF]RIGOR: Dual Governance for Research Intent Integrity in Long-Horizon Autonomous Research▲3.0k2.40
[PDF]Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents▲3952.67
[PDF]FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents▲3952.67
[PDF]TACT: Alleviating Credit Misassignment in Group-Based Policy Optimization for Search Agents with Tool-Aware Credit Transfer▼5.8k2.33
[PDF]Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents▼3.7k2.25
[PDF]RubricAtlas: Decoupling Rubric Discovery from Fact Validation to Optimize Generalist Deep Research Agents▼1.2k3.00
[PDF]Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles▼5.8k2.33
[PDF]Positional Coverage Bias: LLM Coverage Judges Verify Where Content Sits, Not Whether It Is There▼4.3k2.00
[PDF]Are Research Agents Fooled by Clever Hans? A Benchmark for Proactive Pitfall Detection in Medical Autonomous Research▲3.0k2.33
[PDF]ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment▲5.4k3.00
[PDF]VISTA: Learning Wide Search Agents with Verifiable Intermediate States and Turn-Level Credit Assignment▲5103.00
[PDF]Semantic Flashlight: Plan-First Context Construction with Response-Adaptive Evidence Exposure for Deep Research▼4.3k2.00
Withdrawn or desk rejected (26)
[PDF]AskInfer-Bench: Profiles Are Evidence, Not Intent Labels, in Personalized Deep ResearchWithdrawn1.00
[PDF]What to Try, Where to Try It: Online Adaptive Search Policies for Machine Learning Agents.Withdrawn1.33
[PDF]Arxidea: An Agentic System for Personalized Research Ideation and Evidence-Backed VerificationWithdrawn1.67
[PDF]False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search AgentsDesk rejected3.00
[PDF]You Don't Need to Read Papers Anymore: A Provenance-Disciplined Advisory Tier for Autonomous ResearchWithdrawn1.33